mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-03-13 12:41:23 +00:00
Compare commits
20 Commits
feature-ty
...
feature-ti
| Author | SHA1 | Date | |
|---|---|---|---|
|
c7e1981064 | ||
|
|
d6edb6c9f7 | ||
|
|
29ccac98e0 | ||
|
|
8c432afb82 | ||
|
|
a0d0ea28cf | ||
|
|
da76c16274 | ||
|
|
f2eef8a6d1 | ||
|
|
c8e5e6c4e2 | ||
|
|
0b00c66b96 | ||
|
|
e4cadff749 | ||
|
|
d4b6075a2a | ||
|
|
130a73ec71 | ||
|
|
8ebc24bcfa | ||
|
|
d7052b8dee | ||
|
|
c96e9f5dc7 | ||
|
|
f7f162424b | ||
|
|
cdeabaf75d | ||
|
|
404ef6b40d | ||
|
|
8c40491034 | ||
|
|
0f6bdaf5de |
@@ -30,7 +30,7 @@ RUN set -eux \
|
||||
# Purpose: Installs s6-overlay and rootfs
|
||||
# Comments:
|
||||
# - Don't leave anything extra in here either
|
||||
FROM ghcr.io/astral-sh/uv:0.10.9-python3.12-trixie-slim AS s6-overlay-base
|
||||
FROM ghcr.io/astral-sh/uv:0.10.7-python3.12-trixie-slim AS s6-overlay-base
|
||||
|
||||
WORKDIR /usr/src/s6
|
||||
|
||||
|
||||
51
docs/api.md
51
docs/api.md
@@ -305,16 +305,52 @@ The following methods are supported:
|
||||
- `"merge": true or false` (defaults to false)
|
||||
- The `merge` flag determines if the supplied permissions will overwrite all existing permissions (including
|
||||
removing them) or be merged with existing permissions.
|
||||
- `edit_pdf`
|
||||
- Requires `parameters`:
|
||||
- `"doc_ids": [DOCUMENT_ID]` A list of a single document ID to edit.
|
||||
- `"operations": [OPERATION, ...]` A list of operations to perform on the documents. Each operation is a dictionary
|
||||
with the following keys:
|
||||
- `"page": PAGE_NUMBER` The page number to edit (1-based).
|
||||
- `"rotate": DEGREES` Optional rotation in degrees (90, 180, 270).
|
||||
- `"doc": OUTPUT_DOCUMENT_INDEX` Optional index of the output document for split operations.
|
||||
- Optional `parameters`:
|
||||
- `"delete_original": true` to delete the original documents after editing.
|
||||
- `"update_document": true` to add the edited PDF as a new version of the root document.
|
||||
- `"include_metadata": true` to copy metadata from the original document to the edited document.
|
||||
- `remove_password`
|
||||
- Requires `parameters`:
|
||||
- `"password": "PASSWORD_STRING"` The password to remove from the PDF documents.
|
||||
- Optional `parameters`:
|
||||
- `"update_document": true` to add the password-less PDF as a new version of the root document.
|
||||
- `"delete_original": true` to delete the original document after editing.
|
||||
- `"include_metadata": true` to copy metadata from the original document to the new password-less document.
|
||||
- `merge`
|
||||
- No additional `parameters` required.
|
||||
- The ordering of the merged document is determined by the list of IDs.
|
||||
- Optional `parameters`:
|
||||
- `"metadata_document_id": DOC_ID` apply metadata (tags, correspondent, etc.) from this document to the merged document.
|
||||
- `"delete_originals": true` to delete the original documents. This requires the calling user being the owner of
|
||||
all documents that are merged.
|
||||
- `split`
|
||||
- Requires `parameters`:
|
||||
- `"pages": [..]` The list should be a list of pages and/or a ranges, separated by commas e.g. `"[1,2-3,4,5-7]"`
|
||||
- Optional `parameters`:
|
||||
- `"delete_originals": true` to delete the original document after consumption. This requires the calling user being the owner of
|
||||
the document.
|
||||
- The split operation only accepts a single document.
|
||||
- `rotate`
|
||||
- Requires `parameters`:
|
||||
- `"degrees": DEGREES`. Must be an integer i.e. 90, 180, 270
|
||||
- `delete_pages`
|
||||
- Requires `parameters`:
|
||||
- `"pages": [..]` The list should be a list of integers e.g. `"[2,3,4]"`
|
||||
- The delete_pages operation only accepts a single document.
|
||||
- `modify_custom_fields`
|
||||
- Requires `parameters`:
|
||||
- `"add_custom_fields": { CUSTOM_FIELD_ID: VALUE }`: JSON object consisting of custom field id:value pairs to add to the document, can also be a list of custom field IDs
|
||||
to add with empty values.
|
||||
- `"remove_custom_fields": [CUSTOM_FIELD_ID]`: custom field ids to remove from the document.
|
||||
|
||||
#### Document-editing operations
|
||||
|
||||
Beginning with version 10+, the API supports individual endpoints for document-editing operations (`merge`, `rotate`, `edit_pdf`, etc), thus their documentation can be found in the API spec / viewer. Legacy document-editing methods via `/api/documents/bulk_edit/` are still supported for compatibility, are deprecated and clients should migrate to the individual endpoints before they are removed in a future version.
|
||||
|
||||
### Objects
|
||||
|
||||
Bulk editing for objects (tags, document types etc.) currently supports set permissions or delete
|
||||
@@ -431,9 +467,4 @@ Initial API version.
|
||||
#### Version 10
|
||||
|
||||
- The `show_on_dashboard` and `show_in_sidebar` fields of saved views have been
|
||||
removed. Relevant settings are now stored in the UISettings model. Compatibility is maintained
|
||||
for versions < 10 until support for API v9 is dropped.
|
||||
- Document-editing operations such as `merge`, `rotate`, and `edit_pdf` have been
|
||||
moved from the bulk edit endpoint to their own individual endpoints. Using these methods via
|
||||
the bulk edit endpoint is still supported for compatibility with versions < 10 until support
|
||||
for API v9 is dropped.
|
||||
removed. Relevant settings are now stored in the UISettings model.
|
||||
|
||||
@@ -1217,7 +1217,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1758</context>
|
||||
<context context-type="linenumber">1760</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="1577733187050997705" datatype="html">
|
||||
@@ -2802,19 +2802,19 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1759</context>
|
||||
<context context-type="linenumber">1761</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">833</context>
|
||||
<context context-type="linenumber">802</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">871</context>
|
||||
<context context-type="linenumber">835</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">894</context>
|
||||
<context context-type="linenumber">854</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/manage/document-attributes/custom-fields/custom-fields.component.ts</context>
|
||||
@@ -3404,27 +3404,27 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">470</context>
|
||||
<context context-type="linenumber">445</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">510</context>
|
||||
<context context-type="linenumber">485</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">548</context>
|
||||
<context context-type="linenumber">523</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">586</context>
|
||||
<context context-type="linenumber">561</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">648</context>
|
||||
<context context-type="linenumber">623</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">781</context>
|
||||
<context context-type="linenumber">756</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="994016933065248559" datatype="html">
|
||||
@@ -3512,7 +3512,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1812</context>
|
||||
<context context-type="linenumber">1814</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6661109599266152398" datatype="html">
|
||||
@@ -3523,7 +3523,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1813</context>
|
||||
<context context-type="linenumber">1815</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5162686434580248853" datatype="html">
|
||||
@@ -3534,7 +3534,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1814</context>
|
||||
<context context-type="linenumber">1816</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8157388568390631653" datatype="html">
|
||||
@@ -5499,7 +5499,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">785</context>
|
||||
<context context-type="linenumber">760</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4522609911791833187" datatype="html">
|
||||
@@ -7327,7 +7327,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">415</context>
|
||||
<context context-type="linenumber">390</context>
|
||||
</context-group>
|
||||
<note priority="1" from="description">this string is used to separate processing, failed and added on the file upload widget</note>
|
||||
</trans-unit>
|
||||
@@ -7851,7 +7851,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">783</context>
|
||||
<context context-type="linenumber">758</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7295637485862454066" datatype="html">
|
||||
@@ -7869,7 +7869,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">829</context>
|
||||
<context context-type="linenumber">798</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2951161989614003846" datatype="html">
|
||||
@@ -7890,88 +7890,88 @@
|
||||
<source>Reprocess operation for "<x id="PH" equiv-text="this.document.title"/>" will begin in the background.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1385</context>
|
||||
<context context-type="linenumber">1387</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4409560272830824468" datatype="html">
|
||||
<source>Error executing operation</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1396</context>
|
||||
<context context-type="linenumber">1398</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6030453331794586802" datatype="html">
|
||||
<source>Error downloading document</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1459</context>
|
||||
<context context-type="linenumber">1461</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4458954481601077369" datatype="html">
|
||||
<source>Page Fit</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1539</context>
|
||||
<context context-type="linenumber">1541</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4663705961777238777" datatype="html">
|
||||
<source>PDF edit operation for "<x id="PH" equiv-text="this.document.title"/>" will begin in the background.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1779</context>
|
||||
<context context-type="linenumber">1781</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="9043972994040261999" datatype="html">
|
||||
<source>Error executing PDF edit operation</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1791</context>
|
||||
<context context-type="linenumber">1793</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6172690334763056188" datatype="html">
|
||||
<source>Please enter the current password before attempting to remove it.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1802</context>
|
||||
<context context-type="linenumber">1804</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="968660764814228922" datatype="html">
|
||||
<source>Password removal operation for "<x id="PH" equiv-text="this.document.title"/>" will begin in the background.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1836</context>
|
||||
<context context-type="linenumber">1838</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2282118435712883014" datatype="html">
|
||||
<source>Error executing password removal operation</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1850</context>
|
||||
<context context-type="linenumber">1852</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3740891324955700797" datatype="html">
|
||||
<source>Print failed.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1889</context>
|
||||
<context context-type="linenumber">1891</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6457245677384603573" datatype="html">
|
||||
<source>Error loading document for printing.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1901</context>
|
||||
<context context-type="linenumber">1903</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6085793215710522488" datatype="html">
|
||||
<source>An error occurred loading tiff: <x id="PH" equiv-text="err.toString()"/></source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1966</context>
|
||||
<context context-type="linenumber">1968</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1970</context>
|
||||
<context context-type="linenumber">1972</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4958946940233632319" datatype="html">
|
||||
@@ -8215,25 +8215,25 @@
|
||||
<source>Error executing bulk operation</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">321</context>
|
||||
<context context-type="linenumber">294</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7894972847287473517" datatype="html">
|
||||
<source>"<x id="PH" equiv-text="items[0].name"/>"</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">407</context>
|
||||
<context context-type="linenumber">382</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">413</context>
|
||||
<context context-type="linenumber">388</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8639884465898458690" datatype="html">
|
||||
<source>"<x id="PH" equiv-text="items[0].name"/>" and "<x id="PH_1" equiv-text="items[1].name"/>"</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">409</context>
|
||||
<context context-type="linenumber">384</context>
|
||||
</context-group>
|
||||
<note priority="1" from="description">This is for messages like 'modify "tag1" and "tag2"'</note>
|
||||
</trans-unit>
|
||||
@@ -8241,7 +8241,7 @@
|
||||
<source><x id="PH" equiv-text="list"/> and "<x id="PH_1" equiv-text="items[items.length - 1].name"/>"</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">417,419</context>
|
||||
<context context-type="linenumber">392,394</context>
|
||||
</context-group>
|
||||
<note priority="1" from="description">this is for messages like 'modify "tag1", "tag2" and "tag3"'</note>
|
||||
</trans-unit>
|
||||
@@ -8249,14 +8249,14 @@
|
||||
<source>Confirm tags assignment</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">434</context>
|
||||
<context context-type="linenumber">409</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6619516195038467207" datatype="html">
|
||||
<source>This operation will add the tag "<x id="PH" equiv-text="tag.name"/>" to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">440</context>
|
||||
<context context-type="linenumber">415</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="1894412783609570695" datatype="html">
|
||||
@@ -8265,14 +8265,14 @@
|
||||
)"/> to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">445,447</context>
|
||||
<context context-type="linenumber">420,422</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7181166515756808573" datatype="html">
|
||||
<source>This operation will remove the tag "<x id="PH" equiv-text="tag.name"/>" from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">453</context>
|
||||
<context context-type="linenumber">428</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3819792277998068944" datatype="html">
|
||||
@@ -8281,7 +8281,7 @@
|
||||
)"/> from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">458,460</context>
|
||||
<context context-type="linenumber">433,435</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2739066218579571288" datatype="html">
|
||||
@@ -8292,84 +8292,84 @@
|
||||
)"/> on <x id="PH_2" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">462,466</context>
|
||||
<context context-type="linenumber">437,441</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2996713129519325161" datatype="html">
|
||||
<source>Confirm correspondent assignment</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">503</context>
|
||||
<context context-type="linenumber">478</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6900893559485781849" datatype="html">
|
||||
<source>This operation will assign the correspondent "<x id="PH" equiv-text="correspondent.name"/>" to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">505</context>
|
||||
<context context-type="linenumber">480</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="1257522660364398440" datatype="html">
|
||||
<source>This operation will remove the correspondent from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">507</context>
|
||||
<context context-type="linenumber">482</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5393409374423140648" datatype="html">
|
||||
<source>Confirm document type assignment</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">541</context>
|
||||
<context context-type="linenumber">516</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="332180123895325027" datatype="html">
|
||||
<source>This operation will assign the document type "<x id="PH" equiv-text="documentType.name"/>" to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">543</context>
|
||||
<context context-type="linenumber">518</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2236642492594872779" datatype="html">
|
||||
<source>This operation will remove the document type from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">545</context>
|
||||
<context context-type="linenumber">520</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6386555513013840736" datatype="html">
|
||||
<source>Confirm storage path assignment</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">579</context>
|
||||
<context context-type="linenumber">554</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8750527458618415924" datatype="html">
|
||||
<source>This operation will assign the storage path "<x id="PH" equiv-text="storagePath.name"/>" to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">581</context>
|
||||
<context context-type="linenumber">556</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="60728365335056946" datatype="html">
|
||||
<source>This operation will remove the storage path from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">583</context>
|
||||
<context context-type="linenumber">558</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4187352575310415704" datatype="html">
|
||||
<source>Confirm custom field assignment</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">612</context>
|
||||
<context context-type="linenumber">587</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7966494636326273856" datatype="html">
|
||||
<source>This operation will assign the custom field "<x id="PH" equiv-text="customField.name"/>" to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">618</context>
|
||||
<context context-type="linenumber">593</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5789455969634598553" datatype="html">
|
||||
@@ -8378,14 +8378,14 @@
|
||||
)"/> to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">623,625</context>
|
||||
<context context-type="linenumber">598,600</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5648572354333199245" datatype="html">
|
||||
<source>This operation will remove the custom field "<x id="PH" equiv-text="customField.name"/>" from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">631</context>
|
||||
<context context-type="linenumber">606</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6666899594015948817" datatype="html">
|
||||
@@ -8394,7 +8394,7 @@
|
||||
)"/> from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">636,638</context>
|
||||
<context context-type="linenumber">611,613</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8050047262594964176" datatype="html">
|
||||
@@ -8405,91 +8405,91 @@
|
||||
)"/> on <x id="PH_2" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">640,644</context>
|
||||
<context context-type="linenumber">615,619</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8615059324209654051" datatype="html">
|
||||
<source>Move <x id="PH" equiv-text="this.list.selected.size"/> selected document(s) to the trash?</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">782</context>
|
||||
<context context-type="linenumber">757</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8585195717323764335" datatype="html">
|
||||
<source>This operation will permanently recreate the archive files for <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">830</context>
|
||||
<context context-type="linenumber">799</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7366623494074776040" datatype="html">
|
||||
<source>The archive files will be re-generated with the current settings.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">831</context>
|
||||
<context context-type="linenumber">800</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6555329262222566158" datatype="html">
|
||||
<source>Rotate confirm</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">868</context>
|
||||
<context context-type="linenumber">832</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5203024009814367559" datatype="html">
|
||||
<source>This operation will add rotated versions of the <x id="PH" equiv-text="this.list.selected.size"/> document(s).</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">869</context>
|
||||
<context context-type="linenumber">833</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7910756456450124185" datatype="html">
|
||||
<source>Merge confirm</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">892</context>
|
||||
<context context-type="linenumber">852</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7643543647233874431" datatype="html">
|
||||
<source>This operation will merge <x id="PH" equiv-text="this.list.selected.size"/> selected documents into a new document.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">893</context>
|
||||
<context context-type="linenumber">853</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7869008840945899895" datatype="html">
|
||||
<source>Merged document will be queued for consumption.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">916</context>
|
||||
<context context-type="linenumber">872</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="476913782630693351" datatype="html">
|
||||
<source>Custom fields updated.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">940</context>
|
||||
<context context-type="linenumber">896</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3873496751167944011" datatype="html">
|
||||
<source>Error updating custom fields.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">949</context>
|
||||
<context context-type="linenumber">905</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6144801143088984138" datatype="html">
|
||||
<source>Share link bundle creation requested.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">989</context>
|
||||
<context context-type="linenumber">945</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="46019676931295023" datatype="html">
|
||||
<source>Share link bundle creation is not available yet.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
<context context-type="linenumber">996</context>
|
||||
<context context-type="linenumber">952</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6307402210351946694" datatype="html">
|
||||
|
||||
@@ -950,8 +950,8 @@ describe('DocumentDetailComponent', () => {
|
||||
|
||||
it('should support reprocess, confirm and close modal after started', () => {
|
||||
initNormally()
|
||||
const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
|
||||
reprocessSpy.mockReturnValue(of(true))
|
||||
const bulkEditSpy = jest.spyOn(documentService, 'bulkEdit')
|
||||
bulkEditSpy.mockReturnValue(of(true))
|
||||
let openModal: NgbModalRef
|
||||
modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
|
||||
const modalSpy = jest.spyOn(modalService, 'open')
|
||||
@@ -959,7 +959,7 @@ describe('DocumentDetailComponent', () => {
|
||||
component.reprocess()
|
||||
const modalCloseSpy = jest.spyOn(openModal, 'close')
|
||||
openModal.componentInstance.confirmClicked.next()
|
||||
expect(reprocessSpy).toHaveBeenCalledWith([doc.id])
|
||||
expect(bulkEditSpy).toHaveBeenCalledWith([doc.id], 'reprocess', {})
|
||||
expect(modalSpy).toHaveBeenCalled()
|
||||
expect(toastSpy).toHaveBeenCalled()
|
||||
expect(modalCloseSpy).toHaveBeenCalled()
|
||||
@@ -967,13 +967,13 @@ describe('DocumentDetailComponent', () => {
|
||||
|
||||
it('should show error if redo ocr call fails', () => {
|
||||
initNormally()
|
||||
const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
|
||||
const bulkEditSpy = jest.spyOn(documentService, 'bulkEdit')
|
||||
let openModal: NgbModalRef
|
||||
modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
|
||||
const toastSpy = jest.spyOn(toastService, 'showError')
|
||||
component.reprocess()
|
||||
const modalCloseSpy = jest.spyOn(openModal, 'close')
|
||||
reprocessSpy.mockReturnValue(throwError(() => new Error('error occurred')))
|
||||
bulkEditSpy.mockReturnValue(throwError(() => new Error('error occurred')))
|
||||
openModal.componentInstance.confirmClicked.next()
|
||||
expect(toastSpy).toHaveBeenCalled()
|
||||
expect(modalCloseSpy).not.toHaveBeenCalled()
|
||||
@@ -1669,15 +1669,18 @@ describe('DocumentDetailComponent', () => {
|
||||
modal.componentInstance.pages = [{ page: 1, rotate: 0, splitAfter: false }]
|
||||
modal.componentInstance.confirm()
|
||||
let req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/edit_pdf/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [10],
|
||||
operations: [{ page: 1, rotate: 0, doc: 0 }],
|
||||
delete_original: false,
|
||||
update_document: false,
|
||||
include_metadata: true,
|
||||
source_mode: 'explicit_selection',
|
||||
method: 'edit_pdf',
|
||||
parameters: {
|
||||
operations: [{ page: 1, rotate: 0, doc: 0 }],
|
||||
delete_original: false,
|
||||
update_document: false,
|
||||
include_metadata: true,
|
||||
source_mode: 'explicit_selection',
|
||||
},
|
||||
})
|
||||
req.error(new ErrorEvent('failed'))
|
||||
expect(errorSpy).toHaveBeenCalled()
|
||||
@@ -1688,7 +1691,7 @@ describe('DocumentDetailComponent', () => {
|
||||
modal.componentInstance.deleteOriginal = true
|
||||
modal.componentInstance.confirm()
|
||||
req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/edit_pdf/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.flush(true)
|
||||
expect(closeSpy).toHaveBeenCalled()
|
||||
@@ -1708,15 +1711,18 @@ describe('DocumentDetailComponent', () => {
|
||||
dialog.deleteOriginal = true
|
||||
dialog.confirm()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/remove_password/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [10],
|
||||
password: 'secret',
|
||||
update_document: false,
|
||||
include_metadata: false,
|
||||
delete_original: true,
|
||||
source_mode: 'explicit_selection',
|
||||
method: 'remove_password',
|
||||
parameters: {
|
||||
password: 'secret',
|
||||
update_document: false,
|
||||
include_metadata: false,
|
||||
delete_original: true,
|
||||
source_mode: 'explicit_selection',
|
||||
},
|
||||
})
|
||||
req.flush(true)
|
||||
})
|
||||
@@ -1731,7 +1737,7 @@ describe('DocumentDetailComponent', () => {
|
||||
|
||||
expect(errorSpy).toHaveBeenCalled()
|
||||
httpTestingController.expectNone(
|
||||
`${environment.apiBaseUrl}documents/remove_password/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
})
|
||||
|
||||
@@ -1747,7 +1753,7 @@ describe('DocumentDetailComponent', () => {
|
||||
modal.componentInstance as PasswordRemovalConfirmDialogComponent
|
||||
dialog.confirm()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/remove_password/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.error(new ErrorEvent('failed'))
|
||||
|
||||
@@ -1768,7 +1774,7 @@ describe('DocumentDetailComponent', () => {
|
||||
modal.componentInstance as PasswordRemovalConfirmDialogComponent
|
||||
dialog.confirm()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/remove_password/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.flush(true)
|
||||
|
||||
|
||||
@@ -1379,25 +1379,27 @@ export class DocumentDetailComponent
|
||||
modal.componentInstance.btnCaption = $localize`Proceed`
|
||||
modal.componentInstance.confirmClicked.subscribe(() => {
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
this.documentsService.reprocessDocuments([this.document.id]).subscribe({
|
||||
next: () => {
|
||||
this.toastService.showInfo(
|
||||
$localize`Reprocess operation for "${this.document.title}" will begin in the background.`
|
||||
)
|
||||
if (modal) {
|
||||
modal.close()
|
||||
}
|
||||
},
|
||||
error: (error) => {
|
||||
if (modal) {
|
||||
modal.componentInstance.buttonsEnabled = true
|
||||
}
|
||||
this.toastService.showError(
|
||||
$localize`Error executing operation`,
|
||||
error
|
||||
)
|
||||
},
|
||||
})
|
||||
this.documentsService
|
||||
.bulkEdit([this.document.id], 'reprocess', {})
|
||||
.subscribe({
|
||||
next: () => {
|
||||
this.toastService.showInfo(
|
||||
$localize`Reprocess operation for "${this.document.title}" will begin in the background.`
|
||||
)
|
||||
if (modal) {
|
||||
modal.close()
|
||||
}
|
||||
},
|
||||
error: (error) => {
|
||||
if (modal) {
|
||||
modal.componentInstance.buttonsEnabled = true
|
||||
}
|
||||
this.toastService.showError(
|
||||
$localize`Error executing operation`,
|
||||
error
|
||||
)
|
||||
},
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
@@ -1764,7 +1766,7 @@ export class DocumentDetailComponent
|
||||
.subscribe(() => {
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
this.documentsService
|
||||
.editPdfDocuments([sourceDocumentId], {
|
||||
.bulkEdit([sourceDocumentId], 'edit_pdf', {
|
||||
operations: modal.componentInstance.getOperations(),
|
||||
delete_original: modal.componentInstance.deleteOriginal,
|
||||
update_document:
|
||||
@@ -1822,7 +1824,7 @@ export class DocumentDetailComponent
|
||||
dialog.buttonsEnabled = false
|
||||
this.networkActive = true
|
||||
this.documentsService
|
||||
.removePasswordDocuments([sourceDocumentId], {
|
||||
.bulkEdit([sourceDocumentId], 'remove_password', {
|
||||
password: this.password,
|
||||
update_document: dialog.updateDocument,
|
||||
include_metadata: dialog.includeMetadata,
|
||||
|
||||
@@ -849,11 +849,13 @@ describe('BulkEditorComponent', () => {
|
||||
expect(modal).not.toBeUndefined()
|
||||
modal.componentInstance.confirm()
|
||||
let req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/delete/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.flush(true)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [3, 4],
|
||||
method: 'delete',
|
||||
parameters: {},
|
||||
})
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
|
||||
@@ -866,7 +868,7 @@ describe('BulkEditorComponent', () => {
|
||||
fixture.detectChanges()
|
||||
component.applyDelete()
|
||||
req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/delete/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
})
|
||||
|
||||
@@ -942,11 +944,13 @@ describe('BulkEditorComponent', () => {
|
||||
expect(modal).not.toBeUndefined()
|
||||
modal.componentInstance.confirm()
|
||||
let req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/reprocess/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.flush(true)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [3, 4],
|
||||
method: 'reprocess',
|
||||
parameters: {},
|
||||
})
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
|
||||
@@ -975,13 +979,13 @@ describe('BulkEditorComponent', () => {
|
||||
modal.componentInstance.rotate()
|
||||
modal.componentInstance.confirm()
|
||||
let req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/rotate/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.flush(true)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [3, 4],
|
||||
degrees: 90,
|
||||
source_mode: 'latest_version',
|
||||
method: 'rotate',
|
||||
parameters: { degrees: 90 },
|
||||
})
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
|
||||
@@ -1017,12 +1021,13 @@ describe('BulkEditorComponent', () => {
|
||||
modal.componentInstance.metadataDocumentID = 3
|
||||
modal.componentInstance.confirm()
|
||||
let req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/merge/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.flush(true)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [3, 4],
|
||||
metadata_document_id: 3,
|
||||
method: 'merge',
|
||||
parameters: { metadata_document_id: 3 },
|
||||
})
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
|
||||
@@ -1035,13 +1040,13 @@ describe('BulkEditorComponent', () => {
|
||||
modal.componentInstance.deleteOriginals = true
|
||||
modal.componentInstance.confirm()
|
||||
req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/merge/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.flush(true)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [3, 4],
|
||||
metadata_document_id: 3,
|
||||
delete_originals: true,
|
||||
method: 'merge',
|
||||
parameters: { metadata_document_id: 3, delete_originals: true },
|
||||
})
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
|
||||
@@ -1056,13 +1061,13 @@ describe('BulkEditorComponent', () => {
|
||||
modal.componentInstance.archiveFallback = true
|
||||
modal.componentInstance.confirm()
|
||||
req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}documents/merge/`
|
||||
`${environment.apiBaseUrl}documents/bulk_edit/`
|
||||
)
|
||||
req.flush(true)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [3, 4],
|
||||
metadata_document_id: 3,
|
||||
archive_fallback: true,
|
||||
method: 'merge',
|
||||
parameters: { metadata_document_id: 3, archive_fallback: true },
|
||||
})
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
|
||||
|
||||
@@ -12,7 +12,7 @@ import {
|
||||
} from '@ng-bootstrap/ng-bootstrap'
|
||||
import { saveAs } from 'file-saver'
|
||||
import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
|
||||
import { first, map, Observable, Subject, switchMap, takeUntil } from 'rxjs'
|
||||
import { first, map, Subject, switchMap, takeUntil } from 'rxjs'
|
||||
import { ConfirmDialogComponent } from 'src/app/components/common/confirm-dialog/confirm-dialog.component'
|
||||
import { CustomField } from 'src/app/data/custom-field'
|
||||
import { MatchingModel } from 'src/app/data/matching-model'
|
||||
@@ -29,9 +29,7 @@ import { CorrespondentService } from 'src/app/services/rest/correspondent.servic
|
||||
import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
|
||||
import { DocumentTypeService } from 'src/app/services/rest/document-type.service'
|
||||
import {
|
||||
DocumentBulkEditMethod,
|
||||
DocumentService,
|
||||
MergeDocumentsRequest,
|
||||
SelectionDataItem,
|
||||
} from 'src/app/services/rest/document.service'
|
||||
import { SavedViewService } from 'src/app/services/rest/saved-view.service'
|
||||
@@ -257,9 +255,9 @@ export class BulkEditorComponent
|
||||
this.unsubscribeNotifier.complete()
|
||||
}
|
||||
|
||||
private executeBulkEditMethod(
|
||||
private executeBulkOperation(
|
||||
modal: NgbModalRef,
|
||||
method: DocumentBulkEditMethod,
|
||||
method: string,
|
||||
args: any,
|
||||
overrideDocumentIDs?: number[]
|
||||
) {
|
||||
@@ -274,55 +272,32 @@ export class BulkEditorComponent
|
||||
)
|
||||
.pipe(first())
|
||||
.subscribe({
|
||||
next: () => this.handleOperationSuccess(modal),
|
||||
error: (error) => this.handleOperationError(modal, error),
|
||||
next: () => {
|
||||
if (args['delete_originals']) {
|
||||
this.list.selected.clear()
|
||||
}
|
||||
this.list.reload()
|
||||
this.list.reduceSelectionToFilter()
|
||||
this.list.selected.forEach((id) => {
|
||||
this.openDocumentService.refreshDocument(id)
|
||||
})
|
||||
this.savedViewService.maybeRefreshDocumentCounts()
|
||||
if (modal) {
|
||||
modal.close()
|
||||
}
|
||||
},
|
||||
error: (error) => {
|
||||
if (modal) {
|
||||
modal.componentInstance.buttonsEnabled = true
|
||||
}
|
||||
this.toastService.showError(
|
||||
$localize`Error executing bulk operation`,
|
||||
error
|
||||
)
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
private executeDocumentAction(
|
||||
modal: NgbModalRef,
|
||||
request: Observable<any>,
|
||||
options: { deleteOriginals?: boolean } = {}
|
||||
) {
|
||||
if (modal) {
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
}
|
||||
request.pipe(first()).subscribe({
|
||||
next: () => {
|
||||
this.handleOperationSuccess(modal, options.deleteOriginals ?? false)
|
||||
},
|
||||
error: (error) => this.handleOperationError(modal, error),
|
||||
})
|
||||
}
|
||||
|
||||
private handleOperationSuccess(
|
||||
modal: NgbModalRef,
|
||||
clearSelection: boolean = false
|
||||
) {
|
||||
if (clearSelection) {
|
||||
this.list.selected.clear()
|
||||
}
|
||||
this.list.reload()
|
||||
this.list.reduceSelectionToFilter()
|
||||
this.list.selected.forEach((id) => {
|
||||
this.openDocumentService.refreshDocument(id)
|
||||
})
|
||||
this.savedViewService.maybeRefreshDocumentCounts()
|
||||
if (modal) {
|
||||
modal.close()
|
||||
}
|
||||
}
|
||||
|
||||
private handleOperationError(modal: NgbModalRef, error: any) {
|
||||
if (modal) {
|
||||
modal.componentInstance.buttonsEnabled = true
|
||||
}
|
||||
this.toastService.showError(
|
||||
$localize`Error executing bulk operation`,
|
||||
error
|
||||
)
|
||||
}
|
||||
|
||||
private applySelectionData(
|
||||
items: SelectionDataItem[],
|
||||
selectionModel: FilterableDropdownSelectionModel
|
||||
@@ -471,13 +446,13 @@ export class BulkEditorComponent
|
||||
modal.componentInstance.confirmClicked
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
this.executeBulkEditMethod(modal, 'modify_tags', {
|
||||
this.executeBulkOperation(modal, 'modify_tags', {
|
||||
add_tags: changedTags.itemsToAdd.map((t) => t.id),
|
||||
remove_tags: changedTags.itemsToRemove.map((t) => t.id),
|
||||
})
|
||||
})
|
||||
} else {
|
||||
this.executeBulkEditMethod(null, 'modify_tags', {
|
||||
this.executeBulkOperation(null, 'modify_tags', {
|
||||
add_tags: changedTags.itemsToAdd.map((t) => t.id),
|
||||
remove_tags: changedTags.itemsToRemove.map((t) => t.id),
|
||||
})
|
||||
@@ -511,12 +486,12 @@ export class BulkEditorComponent
|
||||
modal.componentInstance.confirmClicked
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
this.executeBulkEditMethod(modal, 'set_correspondent', {
|
||||
this.executeBulkOperation(modal, 'set_correspondent', {
|
||||
correspondent: correspondent ? correspondent.id : null,
|
||||
})
|
||||
})
|
||||
} else {
|
||||
this.executeBulkEditMethod(null, 'set_correspondent', {
|
||||
this.executeBulkOperation(null, 'set_correspondent', {
|
||||
correspondent: correspondent ? correspondent.id : null,
|
||||
})
|
||||
}
|
||||
@@ -549,12 +524,12 @@ export class BulkEditorComponent
|
||||
modal.componentInstance.confirmClicked
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
this.executeBulkEditMethod(modal, 'set_document_type', {
|
||||
this.executeBulkOperation(modal, 'set_document_type', {
|
||||
document_type: documentType ? documentType.id : null,
|
||||
})
|
||||
})
|
||||
} else {
|
||||
this.executeBulkEditMethod(null, 'set_document_type', {
|
||||
this.executeBulkOperation(null, 'set_document_type', {
|
||||
document_type: documentType ? documentType.id : null,
|
||||
})
|
||||
}
|
||||
@@ -587,12 +562,12 @@ export class BulkEditorComponent
|
||||
modal.componentInstance.confirmClicked
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
this.executeBulkEditMethod(modal, 'set_storage_path', {
|
||||
this.executeBulkOperation(modal, 'set_storage_path', {
|
||||
storage_path: storagePath ? storagePath.id : null,
|
||||
})
|
||||
})
|
||||
} else {
|
||||
this.executeBulkEditMethod(null, 'set_storage_path', {
|
||||
this.executeBulkOperation(null, 'set_storage_path', {
|
||||
storage_path: storagePath ? storagePath.id : null,
|
||||
})
|
||||
}
|
||||
@@ -649,7 +624,7 @@ export class BulkEditorComponent
|
||||
modal.componentInstance.confirmClicked
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
this.executeBulkEditMethod(modal, 'modify_custom_fields', {
|
||||
this.executeBulkOperation(modal, 'modify_custom_fields', {
|
||||
add_custom_fields: changedCustomFields.itemsToAdd.map((f) => f.id),
|
||||
remove_custom_fields: changedCustomFields.itemsToRemove.map(
|
||||
(f) => f.id
|
||||
@@ -657,7 +632,7 @@ export class BulkEditorComponent
|
||||
})
|
||||
})
|
||||
} else {
|
||||
this.executeBulkEditMethod(null, 'modify_custom_fields', {
|
||||
this.executeBulkOperation(null, 'modify_custom_fields', {
|
||||
add_custom_fields: changedCustomFields.itemsToAdd.map((f) => f.id),
|
||||
remove_custom_fields: changedCustomFields.itemsToRemove.map(
|
||||
(f) => f.id
|
||||
@@ -787,16 +762,10 @@ export class BulkEditorComponent
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
this.executeDocumentAction(
|
||||
modal,
|
||||
this.documentService.deleteDocuments(Array.from(this.list.selected))
|
||||
)
|
||||
this.executeBulkOperation(modal, 'delete', {})
|
||||
})
|
||||
} else {
|
||||
this.executeDocumentAction(
|
||||
null,
|
||||
this.documentService.deleteDocuments(Array.from(this.list.selected))
|
||||
)
|
||||
this.executeBulkOperation(null, 'delete', {})
|
||||
}
|
||||
}
|
||||
|
||||
@@ -835,12 +804,7 @@ export class BulkEditorComponent
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
this.executeDocumentAction(
|
||||
modal,
|
||||
this.documentService.reprocessDocuments(
|
||||
Array.from(this.list.selected)
|
||||
)
|
||||
)
|
||||
this.executeBulkOperation(modal, 'reprocess', {})
|
||||
})
|
||||
}
|
||||
|
||||
@@ -851,7 +815,7 @@ export class BulkEditorComponent
|
||||
modal.componentInstance.confirmClicked.subscribe(
|
||||
({ permissions, merge }) => {
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
this.executeBulkEditMethod(modal, 'set_permissions', {
|
||||
this.executeBulkOperation(modal, 'set_permissions', {
|
||||
...permissions,
|
||||
merge,
|
||||
})
|
||||
@@ -874,13 +838,9 @@ export class BulkEditorComponent
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
rotateDialog.buttonsEnabled = false
|
||||
this.executeDocumentAction(
|
||||
modal,
|
||||
this.documentService.rotateDocuments(
|
||||
Array.from(this.list.selected),
|
||||
rotateDialog.degrees
|
||||
)
|
||||
)
|
||||
this.executeBulkOperation(modal, 'rotate', {
|
||||
degrees: rotateDialog.degrees,
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
@@ -896,22 +856,18 @@ export class BulkEditorComponent
|
||||
mergeDialog.confirmClicked
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
const args: MergeDocumentsRequest = {}
|
||||
const args = {}
|
||||
if (mergeDialog.metadataDocumentID > -1) {
|
||||
args.metadata_document_id = mergeDialog.metadataDocumentID
|
||||
args['metadata_document_id'] = mergeDialog.metadataDocumentID
|
||||
}
|
||||
if (mergeDialog.deleteOriginals) {
|
||||
args.delete_originals = true
|
||||
args['delete_originals'] = true
|
||||
}
|
||||
if (mergeDialog.archiveFallback) {
|
||||
args.archive_fallback = true
|
||||
args['archive_fallback'] = true
|
||||
}
|
||||
mergeDialog.buttonsEnabled = false
|
||||
this.executeDocumentAction(
|
||||
modal,
|
||||
this.documentService.mergeDocuments(mergeDialog.documentIDs, args),
|
||||
{ deleteOriginals: !!args.delete_originals }
|
||||
)
|
||||
this.executeBulkOperation(modal, 'merge', args, mergeDialog.documentIDs)
|
||||
this.toastService.showInfo(
|
||||
$localize`Merged document will be queued for consumption.`
|
||||
)
|
||||
|
||||
@@ -230,88 +230,6 @@ describe(`DocumentService`, () => {
|
||||
})
|
||||
})
|
||||
|
||||
it('should call appropriate api endpoint for delete documents', () => {
|
||||
const ids = [1, 2, 3]
|
||||
subscription = service.deleteDocuments(ids).subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/delete/`
|
||||
)
|
||||
expect(req.request.method).toEqual('POST')
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
})
|
||||
})
|
||||
|
||||
it('should call appropriate api endpoint for reprocess documents', () => {
|
||||
const ids = [1, 2, 3]
|
||||
subscription = service.reprocessDocuments(ids).subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/reprocess/`
|
||||
)
|
||||
expect(req.request.method).toEqual('POST')
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
})
|
||||
})
|
||||
|
||||
it('should call appropriate api endpoint for rotate documents', () => {
|
||||
const ids = [1, 2, 3]
|
||||
subscription = service.rotateDocuments(ids, 90).subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/rotate/`
|
||||
)
|
||||
expect(req.request.method).toEqual('POST')
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
degrees: 90,
|
||||
source_mode: 'latest_version',
|
||||
})
|
||||
})
|
||||
|
||||
it('should call appropriate api endpoint for merge documents', () => {
|
||||
const ids = [1, 2, 3]
|
||||
const args = { metadata_document_id: 1, delete_originals: true }
|
||||
subscription = service.mergeDocuments(ids, args).subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/merge/`
|
||||
)
|
||||
expect(req.request.method).toEqual('POST')
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
metadata_document_id: 1,
|
||||
delete_originals: true,
|
||||
})
|
||||
})
|
||||
|
||||
it('should call appropriate api endpoint for edit pdf', () => {
|
||||
const ids = [1]
|
||||
const args = { operations: [{ page: 1, rotate: 90, doc: 0 }] }
|
||||
subscription = service.editPdfDocuments(ids, args).subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/edit_pdf/`
|
||||
)
|
||||
expect(req.request.method).toEqual('POST')
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
operations: [{ page: 1, rotate: 90, doc: 0 }],
|
||||
})
|
||||
})
|
||||
|
||||
it('should call appropriate api endpoint for remove password', () => {
|
||||
const ids = [1]
|
||||
const args = { password: 'secret', update_document: true }
|
||||
subscription = service.removePasswordDocuments(ids, args).subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/remove_password/`
|
||||
)
|
||||
expect(req.request.method).toEqual('POST')
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
password: 'secret',
|
||||
update_document: true,
|
||||
})
|
||||
})
|
||||
|
||||
it('should return the correct preview URL for a single document', () => {
|
||||
let url = service.getPreviewUrl(documents[0].id)
|
||||
expect(url).toEqual(
|
||||
|
||||
@@ -42,45 +42,6 @@ export enum BulkEditSourceMode {
|
||||
EXPLICIT_SELECTION = 'explicit_selection',
|
||||
}
|
||||
|
||||
export type DocumentBulkEditMethod =
|
||||
| 'set_correspondent'
|
||||
| 'set_document_type'
|
||||
| 'set_storage_path'
|
||||
| 'add_tag'
|
||||
| 'remove_tag'
|
||||
| 'modify_tags'
|
||||
| 'modify_custom_fields'
|
||||
| 'set_permissions'
|
||||
|
||||
export interface MergeDocumentsRequest {
|
||||
metadata_document_id?: number
|
||||
delete_originals?: boolean
|
||||
archive_fallback?: boolean
|
||||
source_mode?: BulkEditSourceMode
|
||||
}
|
||||
|
||||
export interface EditPdfOperation {
|
||||
page: number
|
||||
rotate?: number
|
||||
doc?: number
|
||||
}
|
||||
|
||||
export interface EditPdfDocumentsRequest {
|
||||
operations: EditPdfOperation[]
|
||||
delete_original?: boolean
|
||||
update_document?: boolean
|
||||
include_metadata?: boolean
|
||||
source_mode?: BulkEditSourceMode
|
||||
}
|
||||
|
||||
export interface RemovePasswordDocumentsRequest {
|
||||
password: string
|
||||
update_document?: boolean
|
||||
delete_original?: boolean
|
||||
include_metadata?: boolean
|
||||
source_mode?: BulkEditSourceMode
|
||||
}
|
||||
|
||||
@Injectable({
|
||||
providedIn: 'root',
|
||||
})
|
||||
@@ -338,7 +299,7 @@ export class DocumentService extends AbstractPaperlessService<Document> {
|
||||
return this.http.get<DocumentMetadata>(url.toString())
|
||||
}
|
||||
|
||||
bulkEdit(ids: number[], method: DocumentBulkEditMethod, args: any) {
|
||||
bulkEdit(ids: number[], method: string, args: any) {
|
||||
return this.http.post(this.getResourceUrl(null, 'bulk_edit'), {
|
||||
documents: ids,
|
||||
method: method,
|
||||
@@ -346,54 +307,6 @@ export class DocumentService extends AbstractPaperlessService<Document> {
|
||||
})
|
||||
}
|
||||
|
||||
deleteDocuments(ids: number[]) {
|
||||
return this.http.post(this.getResourceUrl(null, 'delete'), {
|
||||
documents: ids,
|
||||
})
|
||||
}
|
||||
|
||||
reprocessDocuments(ids: number[]) {
|
||||
return this.http.post(this.getResourceUrl(null, 'reprocess'), {
|
||||
documents: ids,
|
||||
})
|
||||
}
|
||||
|
||||
rotateDocuments(
|
||||
ids: number[],
|
||||
degrees: number,
|
||||
sourceMode: BulkEditSourceMode = BulkEditSourceMode.LATEST_VERSION
|
||||
) {
|
||||
return this.http.post(this.getResourceUrl(null, 'rotate'), {
|
||||
documents: ids,
|
||||
degrees,
|
||||
source_mode: sourceMode,
|
||||
})
|
||||
}
|
||||
|
||||
mergeDocuments(ids: number[], request: MergeDocumentsRequest = {}) {
|
||||
return this.http.post(this.getResourceUrl(null, 'merge'), {
|
||||
documents: ids,
|
||||
...request,
|
||||
})
|
||||
}
|
||||
|
||||
editPdfDocuments(ids: number[], request: EditPdfDocumentsRequest) {
|
||||
return this.http.post(this.getResourceUrl(null, 'edit_pdf'), {
|
||||
documents: ids,
|
||||
...request,
|
||||
})
|
||||
}
|
||||
|
||||
removePasswordDocuments(
|
||||
ids: number[],
|
||||
request: RemovePasswordDocumentsRequest
|
||||
) {
|
||||
return this.http.post(this.getResourceUrl(null, 'remove_password'), {
|
||||
documents: ids,
|
||||
...request,
|
||||
})
|
||||
}
|
||||
|
||||
getSelectionData(ids: number[]): Observable<SelectionData> {
|
||||
return this.http.post<SelectionData>(
|
||||
this.getResourceUrl(null, 'selection_data'),
|
||||
|
||||
@@ -51,11 +51,29 @@ from documents.templating.workflows import parse_w_workflow_placeholders
|
||||
from documents.utils import copy_basic_file_stats
|
||||
from documents.utils import copy_file_with_basic_stats
|
||||
from documents.utils import run_subprocess
|
||||
from paperless.parsers.text import TextDocumentParser
|
||||
from paperless.parsers.tika import TikaDocumentParser
|
||||
from paperless_mail.parsers import MailDocumentParser
|
||||
|
||||
LOGGING_NAME: Final[str] = "paperless.consumer"
|
||||
|
||||
|
||||
def _parser_cleanup(parser: DocumentParser) -> None:
|
||||
"""
|
||||
Call cleanup on a parser, handling the new-style context-manager parsers.
|
||||
|
||||
New-style parsers (e.g. TextDocumentParser) use __exit__ for teardown
|
||||
instead of a cleanup() method. This shim will be removed once all existing parsers
|
||||
have switched to the new style and this consumer is updated to use it
|
||||
|
||||
TODO(stumpylog): Remove me in the future
|
||||
"""
|
||||
if isinstance(parser, (TextDocumentParser, TikaDocumentParser)):
|
||||
parser.__exit__(None, None, None)
|
||||
else:
|
||||
parser.cleanup()
|
||||
|
||||
|
||||
class WorkflowTriggerPlugin(
|
||||
NoCleanupPluginMixin,
|
||||
NoSetupPluginMixin,
|
||||
@@ -138,12 +156,14 @@ class ConsumerPluginMixin:
|
||||
message,
|
||||
current_progress,
|
||||
max_progress,
|
||||
document_id=document_id,
|
||||
owner_id=self.metadata.owner_id if self.metadata.owner_id else None,
|
||||
users_can_view=(self.metadata.view_users or [])
|
||||
+ (self.metadata.change_users or []),
|
||||
groups_can_view=(self.metadata.view_groups or [])
|
||||
+ (self.metadata.change_groups or []),
|
||||
extra_args={
|
||||
"document_id": document_id,
|
||||
"owner_id": self.metadata.owner_id if self.metadata.owner_id else None,
|
||||
"users_can_view": (self.metadata.view_users or [])
|
||||
+ (self.metadata.change_users or []),
|
||||
"groups_can_view": (self.metadata.view_groups or [])
|
||||
+ (self.metadata.change_groups or []),
|
||||
},
|
||||
)
|
||||
|
||||
def _fail(
|
||||
@@ -429,6 +449,12 @@ class ConsumerPlugin(
|
||||
progress_callback=progress_callback,
|
||||
)
|
||||
|
||||
# New-style parsers use __enter__/__exit__ for resource management.
|
||||
# _parser_cleanup (below) handles __exit__; call __enter__ here.
|
||||
# TODO(stumpylog): Remove me in the future
|
||||
if isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
|
||||
document_parser.__enter__()
|
||||
|
||||
self.log.debug(f"Parser: {type(document_parser).__name__}")
|
||||
|
||||
# Parse the document. This may take some time.
|
||||
@@ -457,6 +483,9 @@ class ConsumerPlugin(
|
||||
self.filename,
|
||||
self.input_doc.mailrule_id,
|
||||
)
|
||||
elif isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
|
||||
# TODO(stumpylog): Remove me in the future
|
||||
document_parser.parse(self.working_copy, mime_type)
|
||||
else:
|
||||
document_parser.parse(self.working_copy, mime_type, self.filename)
|
||||
|
||||
@@ -467,11 +496,15 @@ class ConsumerPlugin(
|
||||
ProgressStatusOptions.WORKING,
|
||||
ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
|
||||
)
|
||||
thumbnail = document_parser.get_thumbnail(
|
||||
self.working_copy,
|
||||
mime_type,
|
||||
self.filename,
|
||||
)
|
||||
if isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
|
||||
# TODO(stumpylog): Remove me in the future
|
||||
thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
|
||||
else:
|
||||
thumbnail = document_parser.get_thumbnail(
|
||||
self.working_copy,
|
||||
mime_type,
|
||||
self.filename,
|
||||
)
|
||||
|
||||
text = document_parser.get_text()
|
||||
date = document_parser.get_date()
|
||||
@@ -488,7 +521,7 @@ class ConsumerPlugin(
|
||||
page_count = document_parser.get_page_count(self.working_copy, mime_type)
|
||||
|
||||
except ParseError as e:
|
||||
document_parser.cleanup()
|
||||
_parser_cleanup(document_parser)
|
||||
if tempdir:
|
||||
tempdir.cleanup()
|
||||
self._fail(
|
||||
@@ -498,7 +531,7 @@ class ConsumerPlugin(
|
||||
exception=e,
|
||||
)
|
||||
except Exception as e:
|
||||
document_parser.cleanup()
|
||||
_parser_cleanup(document_parser)
|
||||
if tempdir:
|
||||
tempdir.cleanup()
|
||||
self._fail(
|
||||
@@ -700,7 +733,7 @@ class ConsumerPlugin(
|
||||
exception=e,
|
||||
)
|
||||
finally:
|
||||
document_parser.cleanup()
|
||||
_parser_cleanup(document_parser)
|
||||
tempdir.cleanup()
|
||||
|
||||
self.run_post_consume_script(document)
|
||||
|
||||
@@ -30,6 +30,7 @@ def _process_document(doc_id: int) -> None:
|
||||
)
|
||||
shutil.move(thumb, document.thumbnail_path)
|
||||
finally:
|
||||
# TODO(stumpylog): Cleanup once all parsers are handled
|
||||
parser.cleanup()
|
||||
|
||||
|
||||
|
||||
@@ -1,9 +1,6 @@
|
||||
import enum
|
||||
from collections.abc import Mapping
|
||||
from typing import TYPE_CHECKING
|
||||
from typing import Literal
|
||||
from typing import Self
|
||||
from typing import TypeAlias
|
||||
from typing import TypedDict
|
||||
|
||||
from asgiref.sync import async_to_sync
|
||||
from channels.layers import get_channel_layer
|
||||
@@ -19,59 +16,6 @@ class ProgressStatusOptions(enum.StrEnum):
|
||||
FAILED = "FAILED"
|
||||
|
||||
|
||||
class PermissionsData(TypedDict, total=False):
|
||||
"""Permission fields included in status messages for access control."""
|
||||
|
||||
owner_id: int | None
|
||||
users_can_view: list[int]
|
||||
groups_can_view: list[int]
|
||||
|
||||
|
||||
class ProgressUpdateData(TypedDict):
|
||||
filename: str | None
|
||||
task_id: str | None
|
||||
current_progress: int
|
||||
max_progress: int
|
||||
status: str
|
||||
message: str
|
||||
document_id: int | None
|
||||
owner_id: int | None
|
||||
users_can_view: list[int]
|
||||
groups_can_view: list[int]
|
||||
|
||||
|
||||
class StatusUpdatePayload(TypedDict):
|
||||
type: Literal["status_update"]
|
||||
data: ProgressUpdateData
|
||||
|
||||
|
||||
class DocumentsDeletedData(TypedDict):
|
||||
documents: list[int]
|
||||
|
||||
|
||||
class DocumentsDeletedPayload(TypedDict):
|
||||
type: Literal["documents_deleted"]
|
||||
data: DocumentsDeletedData
|
||||
|
||||
|
||||
class DocumentUpdatedData(TypedDict):
|
||||
document_id: int
|
||||
modified: str
|
||||
owner_id: int | None
|
||||
users_can_view: list[int]
|
||||
groups_can_view: list[int]
|
||||
|
||||
|
||||
class DocumentUpdatedPayload(TypedDict):
|
||||
type: Literal["document_updated"]
|
||||
data: DocumentUpdatedData
|
||||
|
||||
|
||||
WebsocketPayload: TypeAlias = (
|
||||
StatusUpdatePayload | DocumentsDeletedPayload | DocumentUpdatedPayload
|
||||
)
|
||||
|
||||
|
||||
class BaseStatusManager:
|
||||
"""
|
||||
Handles sending of progress information via the channel layer, with proper management
|
||||
@@ -81,11 +25,11 @@ class BaseStatusManager:
|
||||
def __init__(self) -> None:
|
||||
self._channel: RedisPubSubChannelLayer | None = None
|
||||
|
||||
def __enter__(self) -> Self:
|
||||
def __enter__(self):
|
||||
self.open()
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type: object, exc_val: object, exc_tb: object) -> None:
|
||||
def __exit__(self, exc_type, exc_val, exc_tb):
|
||||
self.close()
|
||||
|
||||
def open(self) -> None:
|
||||
@@ -104,7 +48,7 @@ class BaseStatusManager:
|
||||
async_to_sync(self._channel.flush)
|
||||
self._channel = None
|
||||
|
||||
def send(self, payload: WebsocketPayload) -> None:
|
||||
def send(self, payload: Mapping[str, object]) -> None:
|
||||
# Ensure the layer is open
|
||||
self.open()
|
||||
|
||||
@@ -128,36 +72,36 @@ class ProgressManager(BaseStatusManager):
|
||||
message: str,
|
||||
current_progress: int,
|
||||
max_progress: int,
|
||||
*,
|
||||
document_id: int | None = None,
|
||||
owner_id: int | None = None,
|
||||
users_can_view: list[int] | None = None,
|
||||
groups_can_view: list[int] | None = None,
|
||||
extra_args: dict[str, str | int | None] | None = None,
|
||||
) -> None:
|
||||
data: ProgressUpdateData = {
|
||||
data: dict[str, object] = {
|
||||
"filename": self.filename,
|
||||
"task_id": self.task_id,
|
||||
"current_progress": current_progress,
|
||||
"max_progress": max_progress,
|
||||
"status": status,
|
||||
"message": message,
|
||||
"document_id": document_id,
|
||||
"owner_id": owner_id,
|
||||
"users_can_view": users_can_view or [],
|
||||
"groups_can_view": groups_can_view or [],
|
||||
}
|
||||
payload: StatusUpdatePayload = {"type": "status_update", "data": data}
|
||||
if extra_args is not None:
|
||||
data.update(extra_args)
|
||||
|
||||
payload: dict[str, object] = {
|
||||
"type": "status_update",
|
||||
"data": data,
|
||||
}
|
||||
|
||||
self.send(payload)
|
||||
|
||||
|
||||
class DocumentsStatusManager(BaseStatusManager):
|
||||
def send_documents_deleted(self, documents: list[int]) -> None:
|
||||
payload: DocumentsDeletedPayload = {
|
||||
payload: dict[str, object] = {
|
||||
"type": "documents_deleted",
|
||||
"data": {
|
||||
"documents": documents,
|
||||
},
|
||||
}
|
||||
|
||||
self.send(payload)
|
||||
|
||||
def send_document_updated(
|
||||
@@ -169,7 +113,7 @@ class DocumentsStatusManager(BaseStatusManager):
|
||||
users_can_view: list[int] | None = None,
|
||||
groups_can_view: list[int] | None = None,
|
||||
) -> None:
|
||||
payload: DocumentUpdatedPayload = {
|
||||
payload: dict[str, object] = {
|
||||
"type": "document_updated",
|
||||
"data": {
|
||||
"document_id": document_id,
|
||||
@@ -179,4 +123,5 @@ class DocumentsStatusManager(BaseStatusManager):
|
||||
"groups_can_view": groups_can_view or [],
|
||||
},
|
||||
}
|
||||
|
||||
self.send(payload)
|
||||
|
||||
@@ -1540,124 +1540,11 @@ class DocumentListSerializer(serializers.Serializer):
|
||||
return documents
|
||||
|
||||
|
||||
class SourceModeValidationMixin:
|
||||
def validate_source_mode(self, source_mode: str) -> str:
|
||||
if source_mode not in bulk_edit.SourceModeChoices.__dict__.values():
|
||||
raise serializers.ValidationError("Invalid source_mode")
|
||||
return source_mode
|
||||
|
||||
|
||||
class RotateDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
|
||||
degrees = serializers.IntegerField(required=True)
|
||||
source_mode = serializers.CharField(
|
||||
required=False,
|
||||
default=bulk_edit.SourceModeChoices.LATEST_VERSION,
|
||||
)
|
||||
|
||||
|
||||
class MergeDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
|
||||
metadata_document_id = serializers.IntegerField(
|
||||
required=False,
|
||||
allow_null=True,
|
||||
)
|
||||
delete_originals = serializers.BooleanField(required=False, default=False)
|
||||
archive_fallback = serializers.BooleanField(required=False, default=False)
|
||||
source_mode = serializers.CharField(
|
||||
required=False,
|
||||
default=bulk_edit.SourceModeChoices.LATEST_VERSION,
|
||||
)
|
||||
|
||||
|
||||
class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
|
||||
operations = serializers.ListField(required=True)
|
||||
delete_original = serializers.BooleanField(required=False, default=False)
|
||||
update_document = serializers.BooleanField(required=False, default=False)
|
||||
include_metadata = serializers.BooleanField(required=False, default=True)
|
||||
source_mode = serializers.CharField(
|
||||
required=False,
|
||||
default=bulk_edit.SourceModeChoices.LATEST_VERSION,
|
||||
)
|
||||
|
||||
def validate(self, attrs):
|
||||
documents = attrs["documents"]
|
||||
if len(documents) > 1:
|
||||
raise serializers.ValidationError(
|
||||
"Edit PDF method only supports one document",
|
||||
)
|
||||
|
||||
operations = attrs["operations"]
|
||||
if not isinstance(operations, list):
|
||||
raise serializers.ValidationError("operations must be a list")
|
||||
|
||||
for op in operations:
|
||||
if not isinstance(op, dict):
|
||||
raise serializers.ValidationError("invalid operation entry")
|
||||
if "page" not in op or not isinstance(op["page"], int):
|
||||
raise serializers.ValidationError("page must be an integer")
|
||||
if "rotate" in op and not isinstance(op["rotate"], int):
|
||||
raise serializers.ValidationError("rotate must be an integer")
|
||||
if "doc" in op and not isinstance(op["doc"], int):
|
||||
raise serializers.ValidationError("doc must be an integer")
|
||||
|
||||
if attrs["update_document"]:
|
||||
max_idx = max(op.get("doc", 0) for op in operations)
|
||||
if max_idx > 0:
|
||||
raise serializers.ValidationError(
|
||||
"update_document only allowed with a single output document",
|
||||
)
|
||||
|
||||
doc = Document.objects.get(id=documents[0])
|
||||
if doc.page_count:
|
||||
for op in operations:
|
||||
if op["page"] < 1 or op["page"] > doc.page_count:
|
||||
raise serializers.ValidationError(
|
||||
f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
|
||||
)
|
||||
return attrs
|
||||
|
||||
|
||||
class RemovePasswordDocumentsSerializer(
|
||||
DocumentListSerializer,
|
||||
SourceModeValidationMixin,
|
||||
):
|
||||
password = serializers.CharField(required=True)
|
||||
update_document = serializers.BooleanField(required=False, default=False)
|
||||
delete_original = serializers.BooleanField(required=False, default=False)
|
||||
include_metadata = serializers.BooleanField(required=False, default=True)
|
||||
source_mode = serializers.CharField(
|
||||
required=False,
|
||||
default=bulk_edit.SourceModeChoices.LATEST_VERSION,
|
||||
)
|
||||
|
||||
|
||||
class DeleteDocumentsSerializer(DocumentListSerializer):
|
||||
pass
|
||||
|
||||
|
||||
class ReprocessDocumentsSerializer(DocumentListSerializer):
|
||||
pass
|
||||
|
||||
|
||||
class BulkEditSerializer(
|
||||
SerializerWithPerms,
|
||||
DocumentListSerializer,
|
||||
SetPermissionsMixin,
|
||||
SourceModeValidationMixin,
|
||||
):
|
||||
# TODO: remove this and related backwards compatibility code when API v9 is dropped
|
||||
# split, delete_pages can be removed entirely
|
||||
MOVED_DOCUMENT_ACTION_ENDPOINTS = {
|
||||
"delete": "/api/documents/delete/",
|
||||
"reprocess": "/api/documents/reprocess/",
|
||||
"rotate": "/api/documents/rotate/",
|
||||
"merge": "/api/documents/merge/",
|
||||
"edit_pdf": "/api/documents/edit_pdf/",
|
||||
"remove_password": "/api/documents/remove_password/",
|
||||
"split": "/api/documents/edit_pdf/",
|
||||
"delete_pages": "/api/documents/edit_pdf/",
|
||||
}
|
||||
LEGACY_DOCUMENT_ACTION_METHODS = tuple(MOVED_DOCUMENT_ACTION_ENDPOINTS.keys())
|
||||
|
||||
method = serializers.ChoiceField(
|
||||
choices=[
|
||||
"set_correspondent",
|
||||
@@ -1667,8 +1554,15 @@ class BulkEditSerializer(
|
||||
"remove_tag",
|
||||
"modify_tags",
|
||||
"modify_custom_fields",
|
||||
"delete",
|
||||
"reprocess",
|
||||
"set_permissions",
|
||||
*LEGACY_DOCUMENT_ACTION_METHODS,
|
||||
"rotate",
|
||||
"merge",
|
||||
"split",
|
||||
"delete_pages",
|
||||
"edit_pdf",
|
||||
"remove_password",
|
||||
],
|
||||
label="Method",
|
||||
write_only=True,
|
||||
@@ -1746,7 +1640,8 @@ class BulkEditSerializer(
|
||||
return bulk_edit.edit_pdf
|
||||
elif method == "remove_password":
|
||||
return bulk_edit.remove_password
|
||||
else:
|
||||
else: # pragma: no cover
|
||||
# This will never happen as it is handled by the ChoiceField
|
||||
raise serializers.ValidationError("Unsupported method.")
|
||||
|
||||
def _validate_parameters_tags(self, parameters) -> None:
|
||||
@@ -1856,7 +1751,9 @@ class BulkEditSerializer(
|
||||
"source_mode",
|
||||
bulk_edit.SourceModeChoices.LATEST_VERSION,
|
||||
)
|
||||
parameters["source_mode"] = self.validate_source_mode(source_mode)
|
||||
if source_mode not in bulk_edit.SourceModeChoices.__dict__.values():
|
||||
raise serializers.ValidationError("Invalid source_mode")
|
||||
parameters["source_mode"] = source_mode
|
||||
|
||||
def _validate_parameters_split(self, parameters) -> None:
|
||||
if "pages" not in parameters:
|
||||
|
||||
@@ -399,6 +399,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
|
||||
f"Error while parsing document {document} (ID: {document_id})",
|
||||
)
|
||||
finally:
|
||||
# TODO(stumpylog): Cleanup once all parsers are handled
|
||||
parser.cleanup()
|
||||
|
||||
|
||||
|
||||
@@ -422,34 +422,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(args[0], [self.doc1.id])
|
||||
self.assertEqual(len(kwargs), 0)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.delete")
|
||||
def test_delete_documents_endpoint(self, m) -> None:
|
||||
self.setup_mock(m, "delete")
|
||||
response = self.client.post(
|
||||
"/api/documents/delete/",
|
||||
json.dumps({"documents": [self.doc1.id]}),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
m.assert_called_once()
|
||||
args, kwargs = m.call_args
|
||||
self.assertEqual(args[0], [self.doc1.id])
|
||||
self.assertEqual(len(kwargs), 0)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.reprocess")
|
||||
def test_reprocess_documents_endpoint(self, m) -> None:
|
||||
self.setup_mock(m, "reprocess")
|
||||
response = self.client.post(
|
||||
"/api/documents/reprocess/",
|
||||
json.dumps({"documents": [self.doc1.id]}),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
m.assert_called_once()
|
||||
args, kwargs = m.call_args
|
||||
self.assertEqual(args[0], [self.doc1.id])
|
||||
self.assertEqual(len(kwargs), 0)
|
||||
|
||||
@mock.patch("documents.serialisers.bulk_edit.set_storage_path")
|
||||
def test_api_set_storage_path(self, m) -> None:
|
||||
"""
|
||||
@@ -905,7 +877,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(kwargs["merge"], True)
|
||||
|
||||
@mock.patch("documents.serialisers.bulk_edit.set_storage_path")
|
||||
@mock.patch("documents.views.bulk_edit.merge")
|
||||
@mock.patch("documents.serialisers.bulk_edit.merge")
|
||||
def test_insufficient_global_perms(self, mock_merge, mock_set_storage) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
@@ -940,11 +912,12 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
mock_set_storage.assert_not_called()
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/merge/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id],
|
||||
"metadata_document_id": self.doc1.id,
|
||||
"method": "merge",
|
||||
"parameters": {"metadata_document_id": self.doc1.id},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -954,12 +927,15 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
mock_merge.assert_not_called()
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/merge/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id],
|
||||
"metadata_document_id": self.doc1.id,
|
||||
"delete_originals": True,
|
||||
"method": "merge",
|
||||
"parameters": {
|
||||
"metadata_document_id": self.doc1.id,
|
||||
"delete_originals": True,
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1076,117 +1052,84 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
|
||||
m.assert_called_once()
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.rotate")
|
||||
@mock.patch("documents.serialisers.bulk_edit.rotate")
|
||||
def test_rotate(self, m) -> None:
|
||||
self.setup_mock(m, "rotate")
|
||||
response = self.client.post(
|
||||
"/api/documents/rotate/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id, self.doc3.id],
|
||||
"degrees": 90,
|
||||
"method": "rotate",
|
||||
"parameters": {"degrees": 90},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
|
||||
m.assert_called_once()
|
||||
args, kwargs = m.call_args
|
||||
self.assertCountEqual(args[0], [self.doc2.id, self.doc3.id])
|
||||
self.assertEqual(kwargs["degrees"], 90)
|
||||
self.assertEqual(kwargs["source_mode"], "latest_version")
|
||||
self.assertEqual(kwargs["user"], self.user)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.rotate")
|
||||
@mock.patch("documents.serialisers.bulk_edit.rotate")
|
||||
def test_rotate_invalid_params(self, m) -> None:
|
||||
response = self.client.post(
|
||||
"/api/documents/rotate/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id, self.doc3.id],
|
||||
"degrees": "foo",
|
||||
"method": "rotate",
|
||||
"parameters": {"degrees": "foo"},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/rotate/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id, self.doc3.id],
|
||||
"degrees": 90.5,
|
||||
"method": "rotate",
|
||||
"parameters": {"degrees": 90.5},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
|
||||
m.assert_not_called()
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.rotate")
|
||||
def test_rotate_insufficient_permissions(self, m) -> None:
|
||||
self.doc1.owner = User.objects.get(username="temp_admin")
|
||||
self.doc1.save()
|
||||
user1 = User.objects.create(username="user1")
|
||||
user1.user_permissions.add(*Permission.objects.all())
|
||||
user1.save()
|
||||
self.client.force_authenticate(user=user1)
|
||||
|
||||
self.setup_mock(m, "rotate")
|
||||
response = self.client.post(
|
||||
"/api/documents/rotate/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"degrees": 90,
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
|
||||
m.assert_not_called()
|
||||
self.assertEqual(response.content, b"Insufficient permissions")
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/rotate/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id, self.doc3.id],
|
||||
"degrees": 90,
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
m.assert_called_once()
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.merge")
|
||||
@mock.patch("documents.serialisers.bulk_edit.merge")
|
||||
def test_merge(self, m) -> None:
|
||||
self.setup_mock(m, "merge")
|
||||
response = self.client.post(
|
||||
"/api/documents/merge/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id, self.doc3.id],
|
||||
"metadata_document_id": self.doc3.id,
|
||||
"method": "merge",
|
||||
"parameters": {"metadata_document_id": self.doc3.id},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
|
||||
m.assert_called_once()
|
||||
args, kwargs = m.call_args
|
||||
self.assertCountEqual(args[0], [self.doc2.id, self.doc3.id])
|
||||
self.assertEqual(kwargs["metadata_document_id"], self.doc3.id)
|
||||
self.assertEqual(kwargs["source_mode"], "latest_version")
|
||||
self.assertEqual(kwargs["user"], self.user)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.merge")
|
||||
@mock.patch("documents.serialisers.bulk_edit.merge")
|
||||
def test_merge_and_delete_insufficient_permissions(self, m) -> None:
|
||||
self.doc1.owner = User.objects.get(username="temp_admin")
|
||||
self.doc1.save()
|
||||
@@ -1197,12 +1140,15 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
|
||||
self.setup_mock(m, "merge")
|
||||
response = self.client.post(
|
||||
"/api/documents/merge/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"metadata_document_id": self.doc2.id,
|
||||
"delete_originals": True,
|
||||
"method": "merge",
|
||||
"parameters": {
|
||||
"metadata_document_id": self.doc2.id,
|
||||
"delete_originals": True,
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1213,12 +1159,15 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.content, b"Insufficient permissions")
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/merge/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id, self.doc3.id],
|
||||
"metadata_document_id": self.doc2.id,
|
||||
"delete_originals": True,
|
||||
"method": "merge",
|
||||
"parameters": {
|
||||
"metadata_document_id": self.doc2.id,
|
||||
"delete_originals": True,
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1227,15 +1176,27 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
m.assert_called_once()
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.merge")
|
||||
@mock.patch("documents.serialisers.bulk_edit.merge")
|
||||
def test_merge_invalid_parameters(self, m) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API data for merging documents is called
|
||||
- The parameters are invalid
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- The API fails with a correct error code
|
||||
"""
|
||||
self.setup_mock(m, "merge")
|
||||
response = self.client.post(
|
||||
"/api/documents/merge/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"delete_originals": "not_boolean",
|
||||
"method": "merge",
|
||||
"parameters": {
|
||||
"delete_originals": "not_boolean",
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1244,67 +1205,207 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
m.assert_not_called()
|
||||
|
||||
def test_bulk_edit_allows_legacy_file_methods_with_warning(self) -> None:
|
||||
method_payloads = {
|
||||
"delete": {},
|
||||
"reprocess": {},
|
||||
"rotate": {"degrees": 90},
|
||||
"merge": {"metadata_document_id": self.doc2.id},
|
||||
"edit_pdf": {"operations": [{"page": 1}]},
|
||||
"remove_password": {"password": "secret"},
|
||||
"split": {"pages": "1,2-4"},
|
||||
"delete_pages": {"pages": [1, 2]},
|
||||
}
|
||||
|
||||
for version in (9, 10):
|
||||
for method, parameters in method_payloads.items():
|
||||
with self.subTest(method=method, version=version):
|
||||
with mock.patch(
|
||||
f"documents.views.bulk_edit.{method}",
|
||||
) as mocked_method:
|
||||
self.setup_mock(mocked_method, method)
|
||||
with self.assertLogs("paperless.api", level="WARNING") as logs:
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": method,
|
||||
"parameters": parameters,
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
headers={
|
||||
"Accept": f"application/json; version={version}",
|
||||
},
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
mocked_method.assert_called_once()
|
||||
self.assertTrue(
|
||||
any(
|
||||
"Deprecated bulk_edit method" in entry
|
||||
and f"'{method}'" in entry
|
||||
for entry in logs.output
|
||||
),
|
||||
)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.edit_pdf")
|
||||
def test_edit_pdf(self, m) -> None:
|
||||
self.setup_mock(m, "edit_pdf")
|
||||
@mock.patch("documents.serialisers.bulk_edit.split")
|
||||
def test_split(self, m) -> None:
|
||||
self.setup_mock(m, "split")
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": [{"page": 1}],
|
||||
"source_mode": "explicit_selection",
|
||||
"method": "split",
|
||||
"parameters": {"pages": "1,2-4,5-6,7"},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
|
||||
m.assert_called_once()
|
||||
args, kwargs = m.call_args
|
||||
self.assertCountEqual(args[0], [self.doc2.id])
|
||||
self.assertEqual(kwargs["pages"], [[1], [2, 3, 4], [5, 6], [7]])
|
||||
self.assertEqual(kwargs["user"], self.user)
|
||||
|
||||
def test_split_invalid_params(self) -> None:
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "split",
|
||||
"parameters": {}, # pages not specified
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"pages not specified", response.content)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "split",
|
||||
"parameters": {"pages": "1:7"}, # wrong format
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"invalid pages specified", response.content)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [
|
||||
self.doc1.id,
|
||||
self.doc2.id,
|
||||
], # only one document supported
|
||||
"method": "split",
|
||||
"parameters": {"pages": "1-2,3-7"}, # wrong format
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"Split method only supports one document", response.content)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "split",
|
||||
"parameters": {
|
||||
"pages": "1",
|
||||
"delete_originals": "notabool",
|
||||
}, # not a bool
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"delete_originals must be a boolean", response.content)
|
||||
|
||||
@mock.patch("documents.serialisers.bulk_edit.delete_pages")
|
||||
def test_delete_pages(self, m) -> None:
|
||||
self.setup_mock(m, "delete_pages")
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "delete_pages",
|
||||
"parameters": {"pages": [1, 2, 3, 4]},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
|
||||
m.assert_called_once()
|
||||
args, kwargs = m.call_args
|
||||
self.assertCountEqual(args[0], [self.doc2.id])
|
||||
self.assertEqual(kwargs["pages"], [1, 2, 3, 4])
|
||||
|
||||
def test_delete_pages_invalid_params(self) -> None:
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [
|
||||
self.doc1.id,
|
||||
self.doc2.id,
|
||||
], # only one document supported
|
||||
"method": "delete_pages",
|
||||
"parameters": {
|
||||
"pages": [1, 2, 3, 4],
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(
|
||||
b"Delete pages method only supports one document",
|
||||
response.content,
|
||||
)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "delete_pages",
|
||||
"parameters": {}, # pages not specified
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"pages not specified", response.content)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "delete_pages",
|
||||
"parameters": {"pages": "1-3"}, # not a list
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"pages must be a list", response.content)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "delete_pages",
|
||||
"parameters": {"pages": ["1-3"]}, # not ints
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"pages must be a list of integers", response.content)
|
||||
|
||||
@mock.patch("documents.serialisers.bulk_edit.edit_pdf")
|
||||
def test_edit_pdf(self, m) -> None:
|
||||
self.setup_mock(m, "edit_pdf")
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {
|
||||
"operations": [{"page": 1}],
|
||||
"source_mode": "explicit_selection",
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
|
||||
m.assert_called_once()
|
||||
args, kwargs = m.call_args
|
||||
self.assertCountEqual(args[0], [self.doc2.id])
|
||||
@@ -1313,12 +1414,14 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(kwargs["user"], self.user)
|
||||
|
||||
def test_edit_pdf_invalid_params(self) -> None:
|
||||
# multiple documents
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id, self.doc3.id],
|
||||
"operations": [{"page": 1}],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {"operations": [{"page": 1}]},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1326,25 +1429,44 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"Edit PDF method only supports one document", response.content)
|
||||
|
||||
# no operations specified
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": "not_a_list",
|
||||
"method": "edit_pdf",
|
||||
"parameters": {},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"Expected a list of items", response.content)
|
||||
self.assertIn(b"operations not specified", response.content)
|
||||
|
||||
# operations not a list
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": ["invalid_operation"],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {"operations": "not_a_list"},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"operations must be a list", response.content)
|
||||
|
||||
# invalid operation
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {"operations": ["invalid_operation"]},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1352,12 +1474,14 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"invalid operation entry", response.content)
|
||||
|
||||
# page not an int
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": [{"page": "not_an_int"}],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {"operations": [{"page": "not_an_int"}]},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1365,12 +1489,14 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"page must be an integer", response.content)
|
||||
|
||||
# rotate not an int
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": [{"page": 1, "rotate": "not_an_int"}],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {"operations": [{"page": 1, "rotate": "not_an_int"}]},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1378,12 +1504,14 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"rotate must be an integer", response.content)
|
||||
|
||||
# doc not an int
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": [{"page": 1, "doc": "not_an_int"}],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {"operations": [{"page": 1, "doc": "not_an_int"}]},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1391,13 +1519,53 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"doc must be an integer", response.content)
|
||||
|
||||
# update_document not a boolean
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"update_document": True,
|
||||
"operations": [{"page": 1, "doc": 1}, {"page": 2, "doc": 2}],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {
|
||||
"update_document": "not_a_bool",
|
||||
"operations": [{"page": 1}],
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"update_document must be a boolean", response.content)
|
||||
|
||||
# include_metadata not a boolean
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {
|
||||
"include_metadata": "not_a_bool",
|
||||
"operations": [{"page": 1}],
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"include_metadata must be a boolean", response.content)
|
||||
|
||||
# update_document True but output would be multiple documents
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {
|
||||
"update_document": True,
|
||||
"operations": [{"page": 1, "doc": 1}, {"page": 2, "doc": 2}],
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1408,13 +1576,17 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
response.content,
|
||||
)
|
||||
|
||||
# invalid source mode
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": [{"page": 1}],
|
||||
"source_mode": "not_a_mode",
|
||||
"method": "edit_pdf",
|
||||
"parameters": {
|
||||
"operations": [{"page": 1}],
|
||||
"source_mode": "not_a_mode",
|
||||
},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1422,70 +1594,42 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"Invalid source_mode", response.content)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.edit_pdf")
|
||||
@mock.patch("documents.serialisers.bulk_edit.edit_pdf")
|
||||
def test_edit_pdf_page_out_of_bounds(self, m) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API data for editing PDF is called
|
||||
- The page number is out of bounds
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- The API fails with a correct error code
|
||||
"""
|
||||
self.setup_mock(m, "edit_pdf")
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": [{"page": 99}],
|
||||
"method": "edit_pdf",
|
||||
"parameters": {"operations": [{"page": 99}]},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"out of bounds", response.content)
|
||||
m.assert_not_called()
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.edit_pdf")
|
||||
def test_edit_pdf_insufficient_permissions(self, m) -> None:
|
||||
self.doc1.owner = User.objects.get(username="temp_admin")
|
||||
self.doc1.save()
|
||||
user1 = User.objects.create(username="user1")
|
||||
user1.user_permissions.add(*Permission.objects.all())
|
||||
user1.save()
|
||||
self.client.force_authenticate(user=user1)
|
||||
|
||||
self.setup_mock(m, "edit_pdf")
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id],
|
||||
"operations": [{"page": 1}],
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
|
||||
m.assert_not_called()
|
||||
self.assertEqual(response.content, b"Insufficient permissions")
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/edit_pdf/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"operations": [{"page": 1}],
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
m.assert_called_once()
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.remove_password")
|
||||
@mock.patch("documents.serialisers.bulk_edit.remove_password")
|
||||
def test_remove_password(self, m) -> None:
|
||||
self.setup_mock(m, "remove_password")
|
||||
response = self.client.post(
|
||||
"/api/documents/remove_password/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"password": "secret",
|
||||
"update_document": True,
|
||||
"method": "remove_password",
|
||||
"parameters": {"password": "secret", "update_document": True},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
@@ -1497,69 +1641,36 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
self.assertCountEqual(args[0], [self.doc2.id])
|
||||
self.assertEqual(kwargs["password"], "secret")
|
||||
self.assertTrue(kwargs["update_document"])
|
||||
self.assertEqual(kwargs["source_mode"], "latest_version")
|
||||
self.assertEqual(kwargs["user"], self.user)
|
||||
|
||||
def test_remove_password_invalid_params(self) -> None:
|
||||
response = self.client.post(
|
||||
"/api/documents/remove_password/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"method": "remove_password",
|
||||
"parameters": {},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertIn(b"password not specified", response.content)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/remove_password/",
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"password": 123,
|
||||
"method": "remove_password",
|
||||
"parameters": {"password": 123},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.remove_password")
|
||||
def test_remove_password_insufficient_permissions(self, m) -> None:
|
||||
self.doc1.owner = User.objects.get(username="temp_admin")
|
||||
self.doc1.save()
|
||||
user1 = User.objects.create(username="user1")
|
||||
user1.user_permissions.add(*Permission.objects.all())
|
||||
user1.save()
|
||||
self.client.force_authenticate(user=user1)
|
||||
|
||||
self.setup_mock(m, "remove_password")
|
||||
response = self.client.post(
|
||||
"/api/documents/remove_password/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id],
|
||||
"password": "secret",
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
|
||||
m.assert_not_called()
|
||||
self.assertEqual(response.content, b"Insufficient permissions")
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/remove_password/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc2.id],
|
||||
"password": "secret",
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
m.assert_called_once()
|
||||
self.assertIn(b"password must be a string", response.content)
|
||||
|
||||
@override_settings(AUDIT_LOG_ENABLED=True)
|
||||
def test_bulk_edit_audit_log_enabled_simple_field(self) -> None:
|
||||
|
||||
@@ -25,39 +25,3 @@ class TestApiSchema(APITestCase):
|
||||
|
||||
ui_response = self.client.get(self.ENDPOINT + "view/")
|
||||
self.assertEqual(ui_response.status_code, status.HTTP_200_OK)
|
||||
|
||||
def test_schema_includes_dedicated_document_edit_endpoints(self) -> None:
|
||||
schema_response = self.client.get(self.ENDPOINT)
|
||||
self.assertEqual(schema_response.status_code, status.HTTP_200_OK)
|
||||
|
||||
paths = schema_response.data["paths"]
|
||||
self.assertIn("/api/documents/delete/", paths)
|
||||
self.assertIn("/api/documents/reprocess/", paths)
|
||||
self.assertIn("/api/documents/rotate/", paths)
|
||||
self.assertIn("/api/documents/merge/", paths)
|
||||
self.assertIn("/api/documents/edit_pdf/", paths)
|
||||
self.assertIn("/api/documents/remove_password/", paths)
|
||||
|
||||
def test_schema_bulk_edit_advertises_legacy_document_action_methods(self) -> None:
|
||||
schema_response = self.client.get(self.ENDPOINT)
|
||||
self.assertEqual(schema_response.status_code, status.HTTP_200_OK)
|
||||
|
||||
schema = schema_response.data["components"]["schemas"]
|
||||
bulk_schema = schema["BulkEditRequest"]
|
||||
method_schema = bulk_schema["properties"]["method"]
|
||||
|
||||
# drf-spectacular emits the enum as a referenced schema for this field
|
||||
enum_ref = method_schema["allOf"][0]["$ref"].split("/")[-1]
|
||||
advertised_methods = schema[enum_ref]["enum"]
|
||||
|
||||
for action_method in [
|
||||
"delete",
|
||||
"reprocess",
|
||||
"rotate",
|
||||
"merge",
|
||||
"edit_pdf",
|
||||
"remove_password",
|
||||
"split",
|
||||
"delete_pages",
|
||||
]:
|
||||
self.assertIn(action_method, advertised_methods)
|
||||
|
||||
@@ -9,9 +9,9 @@ from documents.parsers import get_default_file_extension
|
||||
from documents.parsers import get_parser_class_for_mime_type
|
||||
from documents.parsers import get_supported_file_extensions
|
||||
from documents.parsers import is_file_ext_supported
|
||||
from paperless.parsers.text import TextDocumentParser
|
||||
from paperless.parsers.tika import TikaDocumentParser
|
||||
from paperless_tesseract.parsers import RasterisedDocumentParser
|
||||
from paperless_text.parsers import TextDocumentParser
|
||||
from paperless_tika.parsers import TikaDocumentParser
|
||||
|
||||
|
||||
class TestParserDiscovery(TestCase):
|
||||
|
||||
@@ -429,11 +429,7 @@ class DummyProgressManager:
|
||||
message: str,
|
||||
current_progress: int,
|
||||
max_progress: int,
|
||||
*,
|
||||
document_id: int | None = None,
|
||||
owner_id: int | None = None,
|
||||
users_can_view: list[int] | None = None,
|
||||
groups_can_view: list[int] | None = None,
|
||||
extra_args: dict[str, str | int] | None = None,
|
||||
) -> None:
|
||||
# Ensure the layer is open
|
||||
self.open()
|
||||
@@ -447,10 +443,9 @@ class DummyProgressManager:
|
||||
"max_progress": max_progress,
|
||||
"status": status,
|
||||
"message": message,
|
||||
"document_id": document_id,
|
||||
"owner_id": owner_id,
|
||||
"users_can_view": users_can_view or [],
|
||||
"groups_can_view": groups_can_view or [],
|
||||
},
|
||||
}
|
||||
if extra_args is not None:
|
||||
payload["data"].update(extra_args)
|
||||
|
||||
self.payloads.append(payload)
|
||||
|
||||
@@ -7,6 +7,7 @@ import tempfile
|
||||
import zipfile
|
||||
from collections import defaultdict
|
||||
from collections import deque
|
||||
from contextlib import nullcontext
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from time import mktime
|
||||
@@ -176,20 +177,14 @@ from documents.serialisers import BulkEditObjectsSerializer
|
||||
from documents.serialisers import BulkEditSerializer
|
||||
from documents.serialisers import CorrespondentSerializer
|
||||
from documents.serialisers import CustomFieldSerializer
|
||||
from documents.serialisers import DeleteDocumentsSerializer
|
||||
from documents.serialisers import DocumentListSerializer
|
||||
from documents.serialisers import DocumentSerializer
|
||||
from documents.serialisers import DocumentTypeSerializer
|
||||
from documents.serialisers import DocumentVersionLabelSerializer
|
||||
from documents.serialisers import DocumentVersionSerializer
|
||||
from documents.serialisers import EditPdfDocumentsSerializer
|
||||
from documents.serialisers import EmailSerializer
|
||||
from documents.serialisers import MergeDocumentsSerializer
|
||||
from documents.serialisers import NotesSerializer
|
||||
from documents.serialisers import PostDocumentSerializer
|
||||
from documents.serialisers import RemovePasswordDocumentsSerializer
|
||||
from documents.serialisers import ReprocessDocumentsSerializer
|
||||
from documents.serialisers import RotateDocumentsSerializer
|
||||
from documents.serialisers import RunTaskViewSerializer
|
||||
from documents.serialisers import SavedViewSerializer
|
||||
from documents.serialisers import SearchResultSerializer
|
||||
@@ -225,6 +220,7 @@ from paperless.celery import app as celery_app
|
||||
from paperless.config import AIConfig
|
||||
from paperless.config import GeneralConfig
|
||||
from paperless.models import ApplicationConfiguration
|
||||
from paperless.parsers import ParserProtocol
|
||||
from paperless.serialisers import GroupSerializer
|
||||
from paperless.serialisers import UserSerializer
|
||||
from paperless.views import StandardPagination
|
||||
@@ -1084,9 +1080,11 @@ class DocumentViewSet(
|
||||
parser_class = get_parser_class_for_mime_type(mime_type)
|
||||
if parser_class:
|
||||
parser = parser_class(progress_callback=None, logging_group=None)
|
||||
cm = parser if isinstance(parser, ParserProtocol) else nullcontext(parser)
|
||||
|
||||
try:
|
||||
return parser.extract_metadata(file, mime_type)
|
||||
with cm:
|
||||
return parser.extract_metadata(file, mime_type)
|
||||
except Exception: # pragma: no cover
|
||||
logger.exception(f"Issue getting metadata for {file}")
|
||||
# TODO: cover GPG errors, remove later.
|
||||
@@ -2120,125 +2118,6 @@ class SavedViewViewSet(BulkPermissionMixin, PassUserMixin, ModelViewSet):
|
||||
ordering_fields = ("name",)
|
||||
|
||||
|
||||
class DocumentOperationPermissionMixin(PassUserMixin):
|
||||
permission_classes = (IsAuthenticated,)
|
||||
parser_classes = (parsers.JSONParser,)
|
||||
METHOD_NAMES_REQUIRING_USER = {
|
||||
"split",
|
||||
"merge",
|
||||
"rotate",
|
||||
"delete_pages",
|
||||
"edit_pdf",
|
||||
"remove_password",
|
||||
}
|
||||
|
||||
def _has_document_permissions(
|
||||
self,
|
||||
*,
|
||||
user: User,
|
||||
documents: list[int],
|
||||
method,
|
||||
parameters: dict[str, Any],
|
||||
) -> bool:
|
||||
if user.is_superuser:
|
||||
return True
|
||||
|
||||
document_objs = Document.objects.select_related("owner").filter(
|
||||
pk__in=documents,
|
||||
)
|
||||
user_is_owner_of_all_documents = all(
|
||||
(doc.owner == user or doc.owner is None) for doc in document_objs
|
||||
)
|
||||
|
||||
# check global and object permissions for all documents
|
||||
has_perms = user.has_perm("documents.change_document") and all(
|
||||
has_perms_owner_aware(user, "change_document", doc) for doc in document_objs
|
||||
)
|
||||
|
||||
# check ownership for methods that change original document
|
||||
if (
|
||||
(
|
||||
has_perms
|
||||
and method
|
||||
in [
|
||||
bulk_edit.set_permissions,
|
||||
bulk_edit.delete,
|
||||
bulk_edit.rotate,
|
||||
bulk_edit.delete_pages,
|
||||
bulk_edit.edit_pdf,
|
||||
bulk_edit.remove_password,
|
||||
]
|
||||
)
|
||||
or (
|
||||
method in [bulk_edit.merge, bulk_edit.split]
|
||||
and parameters.get("delete_originals")
|
||||
)
|
||||
or (method == bulk_edit.edit_pdf and parameters.get("update_document"))
|
||||
):
|
||||
has_perms = user_is_owner_of_all_documents
|
||||
|
||||
# check global add permissions for methods that create documents
|
||||
if (
|
||||
has_perms
|
||||
and (
|
||||
method in [bulk_edit.split, bulk_edit.merge]
|
||||
or (
|
||||
method in [bulk_edit.edit_pdf, bulk_edit.remove_password]
|
||||
and not parameters.get("update_document")
|
||||
)
|
||||
)
|
||||
and not user.has_perm("documents.add_document")
|
||||
):
|
||||
has_perms = False
|
||||
|
||||
# check global delete permissions for methods that delete documents
|
||||
if (
|
||||
has_perms
|
||||
and (
|
||||
method == bulk_edit.delete
|
||||
or (
|
||||
method in [bulk_edit.merge, bulk_edit.split]
|
||||
and parameters.get("delete_originals")
|
||||
)
|
||||
)
|
||||
and not user.has_perm("documents.delete_document")
|
||||
):
|
||||
has_perms = False
|
||||
|
||||
return has_perms
|
||||
|
||||
def _execute_document_action(
|
||||
self,
|
||||
*,
|
||||
method,
|
||||
validated_data: dict[str, Any],
|
||||
operation_label: str,
|
||||
):
|
||||
documents = validated_data["documents"]
|
||||
parameters = {k: v for k, v in validated_data.items() if k != "documents"}
|
||||
user = self.request.user
|
||||
|
||||
if method.__name__ in self.METHOD_NAMES_REQUIRING_USER:
|
||||
parameters["user"] = user
|
||||
|
||||
if not self._has_document_permissions(
|
||||
user=user,
|
||||
documents=documents,
|
||||
method=method,
|
||||
parameters=parameters,
|
||||
):
|
||||
return HttpResponseForbidden("Insufficient permissions")
|
||||
|
||||
try:
|
||||
result = method(documents, **parameters)
|
||||
return Response({"result": result})
|
||||
except Exception as e:
|
||||
logger.warning(f"An error occurred performing {operation_label}: {e!s}")
|
||||
return HttpResponseBadRequest(
|
||||
f"Error performing {operation_label}, check logs for more detail.",
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="bulk_edit",
|
||||
@@ -2257,7 +2136,7 @@ class DocumentOperationPermissionMixin(PassUserMixin):
|
||||
},
|
||||
),
|
||||
)
|
||||
class BulkEditView(DocumentOperationPermissionMixin):
|
||||
class BulkEditView(PassUserMixin):
|
||||
MODIFIED_FIELD_BY_METHOD = {
|
||||
"set_correspondent": "correspondent",
|
||||
"set_document_type": "document_type",
|
||||
@@ -2279,24 +2158,11 @@ class BulkEditView(DocumentOperationPermissionMixin):
|
||||
"remove_password": None,
|
||||
}
|
||||
|
||||
permission_classes = (IsAuthenticated,)
|
||||
serializer_class = BulkEditSerializer
|
||||
parser_classes = (parsers.JSONParser,)
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
request_method = request.data.get("method")
|
||||
api_version = int(request.version or settings.REST_FRAMEWORK["DEFAULT_VERSION"])
|
||||
# TODO: remove this and related backwards compatibility code when API v9 is dropped
|
||||
if request_method in BulkEditSerializer.LEGACY_DOCUMENT_ACTION_METHODS:
|
||||
endpoint = BulkEditSerializer.MOVED_DOCUMENT_ACTION_ENDPOINTS[
|
||||
request_method
|
||||
]
|
||||
logger.warning(
|
||||
"Deprecated bulk_edit method '%s' requested on API version %s. "
|
||||
"Use '%s' instead.",
|
||||
request_method,
|
||||
api_version,
|
||||
endpoint,
|
||||
)
|
||||
|
||||
serializer = self.get_serializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
|
||||
@@ -2304,15 +2170,82 @@ class BulkEditView(DocumentOperationPermissionMixin):
|
||||
method = serializer.validated_data.get("method")
|
||||
parameters = serializer.validated_data.get("parameters")
|
||||
documents = serializer.validated_data.get("documents")
|
||||
if method.__name__ in self.METHOD_NAMES_REQUIRING_USER:
|
||||
if method in [
|
||||
bulk_edit.split,
|
||||
bulk_edit.merge,
|
||||
bulk_edit.rotate,
|
||||
bulk_edit.delete_pages,
|
||||
bulk_edit.edit_pdf,
|
||||
bulk_edit.remove_password,
|
||||
]:
|
||||
parameters["user"] = user
|
||||
if not self._has_document_permissions(
|
||||
user=user,
|
||||
documents=documents,
|
||||
method=method,
|
||||
parameters=parameters,
|
||||
):
|
||||
return HttpResponseForbidden("Insufficient permissions")
|
||||
|
||||
if not user.is_superuser:
|
||||
document_objs = Document.objects.select_related("owner").filter(
|
||||
pk__in=documents,
|
||||
)
|
||||
user_is_owner_of_all_documents = all(
|
||||
(doc.owner == user or doc.owner is None) for doc in document_objs
|
||||
)
|
||||
|
||||
# check global and object permissions for all documents
|
||||
has_perms = user.has_perm("documents.change_document") and all(
|
||||
has_perms_owner_aware(user, "change_document", doc)
|
||||
for doc in document_objs
|
||||
)
|
||||
|
||||
# check ownership for methods that change original document
|
||||
if (
|
||||
(
|
||||
has_perms
|
||||
and method
|
||||
in [
|
||||
bulk_edit.set_permissions,
|
||||
bulk_edit.delete,
|
||||
bulk_edit.rotate,
|
||||
bulk_edit.delete_pages,
|
||||
bulk_edit.edit_pdf,
|
||||
bulk_edit.remove_password,
|
||||
]
|
||||
)
|
||||
or (
|
||||
method in [bulk_edit.merge, bulk_edit.split]
|
||||
and parameters["delete_originals"]
|
||||
)
|
||||
or (method == bulk_edit.edit_pdf and parameters["update_document"])
|
||||
):
|
||||
has_perms = user_is_owner_of_all_documents
|
||||
|
||||
# check global add permissions for methods that create documents
|
||||
if (
|
||||
has_perms
|
||||
and (
|
||||
method in [bulk_edit.split, bulk_edit.merge]
|
||||
or (
|
||||
method in [bulk_edit.edit_pdf, bulk_edit.remove_password]
|
||||
and not parameters["update_document"]
|
||||
)
|
||||
)
|
||||
and not user.has_perm("documents.add_document")
|
||||
):
|
||||
has_perms = False
|
||||
|
||||
# check global delete permissions for methods that delete documents
|
||||
if (
|
||||
has_perms
|
||||
and (
|
||||
method == bulk_edit.delete
|
||||
or (
|
||||
method in [bulk_edit.merge, bulk_edit.split]
|
||||
and parameters["delete_originals"]
|
||||
)
|
||||
)
|
||||
and not user.has_perm("documents.delete_document")
|
||||
):
|
||||
has_perms = False
|
||||
|
||||
if not has_perms:
|
||||
return HttpResponseForbidden("Insufficient permissions")
|
||||
|
||||
try:
|
||||
modified_field = self.MODIFIED_FIELD_BY_METHOD.get(method.__name__, None)
|
||||
@@ -2369,168 +2302,6 @@ class BulkEditView(DocumentOperationPermissionMixin):
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="documents_rotate",
|
||||
description="Rotate one or more documents",
|
||||
responses={
|
||||
200: inline_serializer(
|
||||
name="RotateDocumentsResult",
|
||||
fields={
|
||||
"result": serializers.CharField(),
|
||||
},
|
||||
),
|
||||
},
|
||||
),
|
||||
)
|
||||
class RotateDocumentsView(DocumentOperationPermissionMixin):
|
||||
serializer_class = RotateDocumentsSerializer
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
serializer = self.get_serializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
return self._execute_document_action(
|
||||
method=bulk_edit.rotate,
|
||||
validated_data=serializer.validated_data,
|
||||
operation_label="document rotate",
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="documents_merge",
|
||||
description="Merge selected documents into a new document",
|
||||
responses={
|
||||
200: inline_serializer(
|
||||
name="MergeDocumentsResult",
|
||||
fields={
|
||||
"result": serializers.CharField(),
|
||||
},
|
||||
),
|
||||
},
|
||||
),
|
||||
)
|
||||
class MergeDocumentsView(DocumentOperationPermissionMixin):
|
||||
serializer_class = MergeDocumentsSerializer
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
serializer = self.get_serializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
return self._execute_document_action(
|
||||
method=bulk_edit.merge,
|
||||
validated_data=serializer.validated_data,
|
||||
operation_label="document merge",
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="documents_delete",
|
||||
description="Move selected documents to trash",
|
||||
responses={
|
||||
200: inline_serializer(
|
||||
name="DeleteDocumentsResult",
|
||||
fields={
|
||||
"result": serializers.CharField(),
|
||||
},
|
||||
),
|
||||
},
|
||||
),
|
||||
)
|
||||
class DeleteDocumentsView(DocumentOperationPermissionMixin):
|
||||
serializer_class = DeleteDocumentsSerializer
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
serializer = self.get_serializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
return self._execute_document_action(
|
||||
method=bulk_edit.delete,
|
||||
validated_data=serializer.validated_data,
|
||||
operation_label="document delete",
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="documents_reprocess",
|
||||
description="Reprocess selected documents",
|
||||
responses={
|
||||
200: inline_serializer(
|
||||
name="ReprocessDocumentsResult",
|
||||
fields={
|
||||
"result": serializers.CharField(),
|
||||
},
|
||||
),
|
||||
},
|
||||
),
|
||||
)
|
||||
class ReprocessDocumentsView(DocumentOperationPermissionMixin):
|
||||
serializer_class = ReprocessDocumentsSerializer
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
serializer = self.get_serializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
return self._execute_document_action(
|
||||
method=bulk_edit.reprocess,
|
||||
validated_data=serializer.validated_data,
|
||||
operation_label="document reprocess",
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="documents_edit_pdf",
|
||||
description="Perform PDF edit operations on a selected document",
|
||||
responses={
|
||||
200: inline_serializer(
|
||||
name="EditPdfDocumentsResult",
|
||||
fields={
|
||||
"result": serializers.CharField(),
|
||||
},
|
||||
),
|
||||
},
|
||||
),
|
||||
)
|
||||
class EditPdfDocumentsView(DocumentOperationPermissionMixin):
|
||||
serializer_class = EditPdfDocumentsSerializer
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
serializer = self.get_serializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
return self._execute_document_action(
|
||||
method=bulk_edit.edit_pdf,
|
||||
validated_data=serializer.validated_data,
|
||||
operation_label="PDF edit",
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="documents_remove_password",
|
||||
description="Remove password protection from selected PDFs",
|
||||
responses={
|
||||
200: inline_serializer(
|
||||
name="RemovePasswordDocumentsResult",
|
||||
fields={
|
||||
"result": serializers.CharField(),
|
||||
},
|
||||
),
|
||||
},
|
||||
),
|
||||
)
|
||||
class RemovePasswordDocumentsView(DocumentOperationPermissionMixin):
|
||||
serializer_class = RemovePasswordDocumentsSerializer
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
serializer = self.get_serializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
return self._execute_document_action(
|
||||
method=bulk_edit.remove_password,
|
||||
validated_data=serializer.validated_data,
|
||||
operation_label="password removal",
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
description="Upload a document via the API",
|
||||
|
||||
@@ -2,7 +2,7 @@ msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: paperless-ngx\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2026-03-10 18:57+0000\n"
|
||||
"POT-Creation-Date: 2026-03-09 22:37+0000\n"
|
||||
"PO-Revision-Date: 2022-02-17 04:17\n"
|
||||
"Last-Translator: \n"
|
||||
"Language-Team: English\n"
|
||||
@@ -1299,7 +1299,7 @@ msgstr ""
|
||||
msgid "workflow runs"
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:463 documents/serialisers.py:2470
|
||||
#: documents/serialisers.py:463 documents/serialisers.py:2367
|
||||
msgid "Insufficient permissions."
|
||||
msgstr ""
|
||||
|
||||
@@ -1307,39 +1307,39 @@ msgstr ""
|
||||
msgid "Invalid color."
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2093
|
||||
#: documents/serialisers.py:1990
|
||||
#, python-format
|
||||
msgid "File type %(type)s not supported"
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2137
|
||||
#: documents/serialisers.py:2034
|
||||
#, python-format
|
||||
msgid "Custom field id must be an integer: %(id)s"
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2144
|
||||
#: documents/serialisers.py:2041
|
||||
#, python-format
|
||||
msgid "Custom field with id %(id)s does not exist"
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2161 documents/serialisers.py:2171
|
||||
#: documents/serialisers.py:2058 documents/serialisers.py:2068
|
||||
msgid ""
|
||||
"Custom fields must be a list of integers or an object mapping ids to values."
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2166
|
||||
#: documents/serialisers.py:2063
|
||||
msgid "Some custom fields don't exist or were specified twice."
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2313
|
||||
#: documents/serialisers.py:2210
|
||||
msgid "Invalid variable detected."
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2526
|
||||
#: documents/serialisers.py:2423
|
||||
msgid "Duplicate document identifiers are not allowed."
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2556 documents/views.py:3561
|
||||
#: documents/serialisers.py:2453 documents/views.py:3328
|
||||
#, python-format
|
||||
msgid "Documents not found: %(ids)s"
|
||||
msgstr ""
|
||||
@@ -1603,20 +1603,20 @@ msgstr ""
|
||||
msgid "Unable to parse URI {value}"
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:3573
|
||||
#: documents/views.py:3340
|
||||
#, python-format
|
||||
msgid "Insufficient permissions to share document %(id)s."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:3616
|
||||
#: documents/views.py:3383
|
||||
msgid "Bundle is already being processed."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:3673
|
||||
#: documents/views.py:3440
|
||||
msgid "The share link bundle is still being prepared. Please try again later."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:3683
|
||||
#: documents/views.py:3450
|
||||
msgid "The share link bundle is unavailable."
|
||||
msgstr ""
|
||||
|
||||
@@ -2004,7 +2004,7 @@ msgstr ""
|
||||
msgid "Chinese Traditional"
|
||||
msgstr ""
|
||||
|
||||
#: paperless/urls.py:415
|
||||
#: paperless/urls.py:379
|
||||
msgid "Paperless-ngx administration"
|
||||
msgstr ""
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
import os
|
||||
|
||||
from celery import Celery
|
||||
from celery.signals import worker_process_init
|
||||
|
||||
# Set the default Django settings module for the 'celery' program.
|
||||
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "paperless.settings")
|
||||
@@ -15,3 +16,19 @@ app.config_from_object("django.conf:settings", namespace="CELERY")
|
||||
|
||||
# Load task modules from all registered Django apps.
|
||||
app.autodiscover_tasks()
|
||||
|
||||
|
||||
@worker_process_init.connect
|
||||
def on_worker_process_init(**kwargs) -> None: # pragma: no cover
|
||||
"""
|
||||
Register built-in parsers eagerly in each Celery worker process.
|
||||
|
||||
This registers only the built-in parsers (no entrypoint discovery) so
|
||||
that workers can begin consuming documents immediately. Entrypoint
|
||||
discovery for third-party parsers is deferred to the first call of
|
||||
get_parser_registry() inside a task, keeping worker_process_init
|
||||
well within its 4-second timeout budget.
|
||||
"""
|
||||
from paperless.parsers.registry import init_builtin_parsers
|
||||
|
||||
init_builtin_parsers()
|
||||
|
||||
@@ -1,61 +1,62 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import TYPE_CHECKING
|
||||
from typing import Any
|
||||
|
||||
from channels.generic.websocket import AsyncWebsocketConsumer
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from documents.plugins.helpers import PermissionsData
|
||||
from asgiref.sync import async_to_sync
|
||||
from channels.exceptions import AcceptConnection
|
||||
from channels.exceptions import DenyConnection
|
||||
from channels.generic.websocket import WebsocketConsumer
|
||||
|
||||
|
||||
class StatusConsumer(AsyncWebsocketConsumer):
|
||||
def _authenticated(self) -> bool:
|
||||
user: Any = self.scope.get("user")
|
||||
return user is not None and user.is_authenticated
|
||||
class StatusConsumer(WebsocketConsumer):
|
||||
def _authenticated(self):
|
||||
return "user" in self.scope and self.scope["user"].is_authenticated
|
||||
|
||||
async def _can_view(self, data: PermissionsData) -> bool:
|
||||
user: Any = self.scope.get("user")
|
||||
if user is None:
|
||||
return False
|
||||
def _can_view(self, data):
|
||||
user = self.scope.get("user") if self.scope.get("user") else None
|
||||
owner_id = data.get("owner_id")
|
||||
users_can_view = data.get("users_can_view", [])
|
||||
groups_can_view = data.get("groups_can_view", [])
|
||||
return (
|
||||
user.is_superuser
|
||||
or user.id == owner_id
|
||||
or user.id in users_can_view
|
||||
or any(
|
||||
user.groups.filter(pk=group_id).exists() for group_id in groups_can_view
|
||||
)
|
||||
)
|
||||
|
||||
if user.is_superuser or user.id == owner_id or user.id in users_can_view:
|
||||
return True
|
||||
|
||||
for group_id in groups_can_view:
|
||||
if await user.groups.filter(pk=group_id).aexists():
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
async def connect(self) -> None:
|
||||
def connect(self):
|
||||
if not self._authenticated():
|
||||
await self.close()
|
||||
return
|
||||
await self.channel_layer.group_add("status_updates", self.channel_name)
|
||||
await self.accept()
|
||||
|
||||
async def disconnect(self, code: int) -> None:
|
||||
await self.channel_layer.group_discard("status_updates", self.channel_name)
|
||||
|
||||
async def status_update(self, event: dict[str, Any]) -> None:
|
||||
if not self._authenticated():
|
||||
await self.close()
|
||||
elif await self._can_view(event["data"]):
|
||||
await self.send(json.dumps(event))
|
||||
|
||||
async def documents_deleted(self, event: dict[str, Any]) -> None:
|
||||
if not self._authenticated():
|
||||
await self.close()
|
||||
raise DenyConnection
|
||||
else:
|
||||
await self.send(json.dumps(event))
|
||||
async_to_sync(self.channel_layer.group_add)(
|
||||
"status_updates",
|
||||
self.channel_name,
|
||||
)
|
||||
raise AcceptConnection
|
||||
|
||||
async def document_updated(self, event: dict[str, Any]) -> None:
|
||||
def disconnect(self, close_code) -> None:
|
||||
async_to_sync(self.channel_layer.group_discard)(
|
||||
"status_updates",
|
||||
self.channel_name,
|
||||
)
|
||||
|
||||
def status_update(self, event) -> None:
|
||||
if not self._authenticated():
|
||||
await self.close()
|
||||
elif await self._can_view(event["data"]):
|
||||
await self.send(json.dumps(event))
|
||||
self.close()
|
||||
else:
|
||||
if self._can_view(event["data"]):
|
||||
self.send(json.dumps(event))
|
||||
|
||||
def documents_deleted(self, event) -> None:
|
||||
if not self._authenticated():
|
||||
self.close()
|
||||
else:
|
||||
self.send(json.dumps(event))
|
||||
|
||||
def document_updated(self, event: Any) -> None:
|
||||
if not self._authenticated():
|
||||
self.close()
|
||||
else:
|
||||
if self._can_view(event["data"]):
|
||||
self.send(json.dumps(event))
|
||||
|
||||
379
src/paperless/parsers/__init__.py
Normal file
379
src/paperless/parsers/__init__.py
Normal file
@@ -0,0 +1,379 @@
|
||||
"""
|
||||
Public interface for the Paperless-ngx parser plugin system.
|
||||
|
||||
This module defines ParserProtocol — the structural contract that every
|
||||
document parser must satisfy, whether it is a built-in parser shipped with
|
||||
Paperless-ngx or a third-party parser installed via a Python entrypoint.
|
||||
|
||||
Phase 1/2 scope: only the Protocol is defined here. The transitional
|
||||
DocumentParser ABC (Phase 3) and concrete built-in parsers (Phase 3+) will
|
||||
be added in later phases, so there are intentionally no imports of parser
|
||||
implementations here.
|
||||
|
||||
Usage example (third-party parser)::
|
||||
|
||||
from paperless.parsers import ParserProtocol
|
||||
|
||||
class MyParser:
|
||||
name = "my-parser"
|
||||
version = "1.0.0"
|
||||
author = "Acme Corp"
|
||||
url = "https://example.com/my-parser"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls) -> dict[str, str]:
|
||||
return {"application/x-my-format": ".myf"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 10
|
||||
|
||||
# … implement remaining protocol methods …
|
||||
|
||||
assert isinstance(MyParser(), ParserProtocol)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
from typing import Protocol
|
||||
from typing import Self
|
||||
from typing import TypedDict
|
||||
from typing import runtime_checkable
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import datetime
|
||||
from pathlib import Path
|
||||
from types import TracebackType
|
||||
|
||||
__all__ = [
|
||||
"MetadataEntry",
|
||||
"ParserProtocol",
|
||||
]
|
||||
|
||||
|
||||
class MetadataEntry(TypedDict):
|
||||
"""A single metadata field extracted from a document.
|
||||
|
||||
All four keys are required. Values are always serialised to strings —
|
||||
type-specific conversion (dates, integers, lists) is the responsibility
|
||||
of the parser before returning.
|
||||
"""
|
||||
|
||||
namespace: str
|
||||
"""URI of the metadata namespace (e.g. 'http://ns.adobe.com/pdf/1.3/')."""
|
||||
|
||||
prefix: str
|
||||
"""Conventional namespace prefix (e.g. 'pdf', 'xmp', 'dc')."""
|
||||
|
||||
key: str
|
||||
"""Field name within the namespace (e.g. 'Author', 'CreateDate')."""
|
||||
|
||||
value: str
|
||||
"""String representation of the field value."""
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class ParserProtocol(Protocol):
|
||||
"""Structural contract for all Paperless-ngx document parsers.
|
||||
|
||||
Both built-in parsers and third-party plugins (discovered via the
|
||||
"paperless_ngx.parsers" entrypoint group) must satisfy this Protocol.
|
||||
Because it is decorated with runtime_checkable, isinstance(obj,
|
||||
ParserProtocol) works at runtime based on method presence, which is
|
||||
useful for validation in ParserRegistry.discover.
|
||||
|
||||
Parsers must expose four string attributes at the class level so the
|
||||
registry can log attribution information without instantiating the parser:
|
||||
|
||||
name : str
|
||||
Human-readable parser name (e.g. "Tesseract OCR").
|
||||
version : str
|
||||
Semantic version string (e.g. "1.2.3").
|
||||
author : str
|
||||
Author or organisation name.
|
||||
url : str
|
||||
URL for documentation, source code, or issue tracker.
|
||||
"""
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Class-level identity (checked by the registry, not Protocol methods)
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
name: str
|
||||
version: str
|
||||
author: str
|
||||
url: str
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Class methods
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls) -> dict[str, str]:
|
||||
"""Return a mapping of supported MIME types to preferred file extensions.
|
||||
|
||||
The keys are MIME type strings (e.g. "application/pdf"), and the
|
||||
values are the preferred file extension including the leading dot
|
||||
(e.g. ".pdf"). The registry uses this mapping both to decide whether
|
||||
a parser is a candidate for a given file and to determine the default
|
||||
extension when creating archive copies.
|
||||
|
||||
Returns
|
||||
-------
|
||||
dict[str, str]
|
||||
{mime_type: extension} mapping — may be empty if the parser
|
||||
has been temporarily disabled.
|
||||
"""
|
||||
...
|
||||
|
||||
@classmethod
|
||||
def score(
|
||||
cls,
|
||||
mime_type: str,
|
||||
filename: str,
|
||||
path: Path | None = None,
|
||||
) -> int | None:
|
||||
"""Return a priority score for handling this file, or None to decline.
|
||||
|
||||
The registry calls this after confirming that the MIME type is in
|
||||
supported_mime_types. Parsers may inspect filename and optionally
|
||||
the file at path to refine their confidence level.
|
||||
|
||||
A higher score wins. Return None to explicitly decline handling a file
|
||||
even though the MIME type is listed as supported (e.g. when a feature
|
||||
flag is disabled, or a required service is not configured).
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mime_type:
|
||||
The detected MIME type of the file to be parsed.
|
||||
filename:
|
||||
The original filename, including extension.
|
||||
path:
|
||||
Optional filesystem path to the file. Parsers that need to
|
||||
inspect file content (e.g. magic-byte sniffing) may use this.
|
||||
May be None when scoring happens before the file is available locally.
|
||||
|
||||
Returns
|
||||
-------
|
||||
int | None
|
||||
Priority score (higher wins), or None to decline.
|
||||
"""
|
||||
...
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Properties
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@property
|
||||
def can_produce_archive(self) -> bool:
|
||||
"""Whether this parser can produce a searchable PDF archive copy.
|
||||
|
||||
If True, the consumption pipeline may request an archive version when
|
||||
processing the document, subject to the ARCHIVE_FILE_GENERATION
|
||||
setting. If False, only thumbnail and text extraction are performed.
|
||||
"""
|
||||
...
|
||||
|
||||
@property
|
||||
def requires_pdf_rendition(self) -> bool:
|
||||
"""Whether the parser must produce a PDF for the frontend to display.
|
||||
|
||||
True for formats the browser cannot display natively (e.g. DOCX, ODT).
|
||||
When True, the pipeline always stores the PDF output regardless of the
|
||||
ARCHIVE_FILE_GENERATION setting, since the original format cannot be
|
||||
shown to the user.
|
||||
"""
|
||||
...
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Core parsing interface
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def parse(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
*,
|
||||
produce_archive: bool = True,
|
||||
) -> None:
|
||||
"""Parse document_path and populate internal state.
|
||||
|
||||
After a successful call, callers retrieve results via get_text,
|
||||
get_date, and get_archive_path.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the document file to parse.
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
produce_archive:
|
||||
When True (the default) and can_produce_archive is also True,
|
||||
the parser should produce a searchable PDF at the path returned
|
||||
by get_archive_path. Pass False when only text extraction and
|
||||
thumbnail generation are required and disk I/O should be minimised.
|
||||
|
||||
Raises
|
||||
------
|
||||
documents.parsers.ParseError
|
||||
If parsing fails for any reason.
|
||||
"""
|
||||
...
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Result accessors
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def get_text(self) -> str | None:
|
||||
"""Return the plain-text content extracted during parse.
|
||||
|
||||
Returns
|
||||
-------
|
||||
str | None
|
||||
Extracted text, or None if no text could be found.
|
||||
"""
|
||||
...
|
||||
|
||||
def get_date(self) -> datetime.datetime | None:
|
||||
"""Return the document date detected during parse.
|
||||
|
||||
Returns
|
||||
-------
|
||||
datetime.datetime | None
|
||||
Detected document date, or None if no date was found.
|
||||
"""
|
||||
...
|
||||
|
||||
def get_archive_path(self) -> Path | None:
|
||||
"""Return the path to the generated archive PDF, or None.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path | None
|
||||
Path to the searchable PDF archive, or None if no archive was
|
||||
produced (e.g. because produce_archive=False or the parser does
|
||||
not support archive generation).
|
||||
"""
|
||||
...
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Thumbnail and metadata
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
|
||||
"""Generate and return the path to a thumbnail image for the document.
|
||||
|
||||
May be called independently of parse. The returned path must point to
|
||||
an existing WebP image file inside the parser's temporary working
|
||||
directory.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the source document.
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Path to the generated thumbnail image (WebP format preferred).
|
||||
"""
|
||||
...
|
||||
|
||||
def get_page_count(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> int | None:
|
||||
"""Return the number of pages in the document, if determinable.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the source document.
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
|
||||
Returns
|
||||
-------
|
||||
int | None
|
||||
Page count, or None if the parser cannot determine it.
|
||||
"""
|
||||
...
|
||||
|
||||
def extract_metadata(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> list[MetadataEntry]:
|
||||
"""Extract format-specific metadata from the document.
|
||||
|
||||
Called by the API view layer on demand — not during the consumption
|
||||
pipeline. Results are returned to the frontend for per-file display.
|
||||
|
||||
For documents with an archive version, this method is called twice:
|
||||
once for the original file (with its native MIME type) and once for
|
||||
the archive file (with ``"application/pdf"``). Parsers that produce
|
||||
archives should handle both cases.
|
||||
|
||||
Implementations must not raise. A failure to read metadata is not
|
||||
fatal — log a warning and return whatever partial results were
|
||||
collected, or ``[]`` if none.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the file to extract metadata from.
|
||||
mime_type:
|
||||
MIME type of the file at ``document_path``. May be
|
||||
``"application/pdf"`` when called for the archive version.
|
||||
|
||||
Returns
|
||||
-------
|
||||
list[MetadataEntry]
|
||||
Zero or more metadata entries. Returns ``[]`` if no metadata
|
||||
could be extracted or the format does not support it.
|
||||
"""
|
||||
...
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Context manager
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def __enter__(self) -> Self:
|
||||
"""Enter the parser context, returning the parser instance.
|
||||
|
||||
Implementations should perform any resource allocation here if not
|
||||
done in __init__ (e.g. creating API clients or temp directories).
|
||||
|
||||
Returns
|
||||
-------
|
||||
Self
|
||||
The parser instance itself.
|
||||
"""
|
||||
...
|
||||
|
||||
def __exit__(
|
||||
self,
|
||||
exc_type: type[BaseException] | None,
|
||||
exc_val: BaseException | None,
|
||||
exc_tb: TracebackType | None,
|
||||
) -> None:
|
||||
"""Exit the parser context and release all resources.
|
||||
|
||||
Implementations must clean up all temporary files and other resources
|
||||
regardless of whether an exception occurred.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
exc_type:
|
||||
The exception class, or None if no exception was raised.
|
||||
exc_val:
|
||||
The exception instance, or None.
|
||||
exc_tb:
|
||||
The traceback, or None.
|
||||
"""
|
||||
...
|
||||
364
src/paperless/parsers/registry.py
Normal file
364
src/paperless/parsers/registry.py
Normal file
@@ -0,0 +1,364 @@
|
||||
"""
|
||||
Singleton registry that tracks all document parsers available to
|
||||
Paperless-ngx — both built-ins shipped with the application and third-party
|
||||
plugins installed via Python entrypoints.
|
||||
|
||||
Public surface
|
||||
--------------
|
||||
get_parser_registry
|
||||
Lazy-initialise and return the shared ParserRegistry. This is the primary
|
||||
entry point for production code.
|
||||
|
||||
init_builtin_parsers
|
||||
Register built-in parsers only, without entrypoint discovery. Safe to
|
||||
call from Celery worker_process_init where importing all entrypoints
|
||||
would be wasteful or cause side effects.
|
||||
|
||||
reset_parser_registry
|
||||
Reset module-level state. For tests only.
|
||||
|
||||
Entrypoint group
|
||||
----------------
|
||||
Third-party parsers must advertise themselves under the
|
||||
"paperless_ngx.parsers" entrypoint group in their pyproject.toml::
|
||||
|
||||
[project.entry-points."paperless_ngx.parsers"]
|
||||
my_parser = "my_package.parsers:MyParser"
|
||||
|
||||
The loaded class must expose the following attributes at the class level
|
||||
(not just on instances) for the registry to accept it:
|
||||
name, version, author, url, supported_mime_types (callable), score (callable).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from importlib.metadata import entry_points
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from pathlib import Path
|
||||
|
||||
from paperless.parsers import ParserProtocol
|
||||
|
||||
logger = logging.getLogger("paperless.parsers.registry")
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Module-level singleton state
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_registry: ParserRegistry | None = None
|
||||
_discovery_complete: bool = False
|
||||
|
||||
# Attribute names that every registered external parser class must expose.
|
||||
_REQUIRED_ATTRS: tuple[str, ...] = (
|
||||
"name",
|
||||
"version",
|
||||
"author",
|
||||
"url",
|
||||
"supported_mime_types",
|
||||
"score",
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Module-level accessor functions
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def get_parser_registry() -> ParserRegistry:
|
||||
"""Return the shared ParserRegistry instance.
|
||||
|
||||
On the first call this function:
|
||||
|
||||
1. Creates a new ParserRegistry.
|
||||
2. Calls register_defaults to install built-in parsers.
|
||||
3. Calls discover to load third-party plugins via importlib.metadata entrypoints.
|
||||
4. Calls log_summary to emit a startup summary.
|
||||
|
||||
Subsequent calls return the same instance immediately.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ParserRegistry
|
||||
The shared registry singleton.
|
||||
"""
|
||||
global _registry, _discovery_complete
|
||||
|
||||
if _registry is None:
|
||||
_registry = ParserRegistry()
|
||||
_registry.register_defaults()
|
||||
|
||||
if not _discovery_complete:
|
||||
_registry.discover()
|
||||
_registry.log_summary()
|
||||
_discovery_complete = True
|
||||
|
||||
return _registry
|
||||
|
||||
|
||||
def init_builtin_parsers() -> None:
|
||||
"""Register built-in parsers without performing entrypoint discovery.
|
||||
|
||||
Intended for use in Celery worker_process_init handlers where importing
|
||||
all installed entrypoints would be wasteful, slow, or could produce
|
||||
undesirable side effects. Entrypoint discovery (third-party plugins) is
|
||||
deliberately not performed.
|
||||
|
||||
Safe to call multiple times — subsequent calls are no-ops.
|
||||
|
||||
Returns
|
||||
-------
|
||||
None
|
||||
"""
|
||||
global _registry
|
||||
|
||||
if _registry is None:
|
||||
_registry = ParserRegistry()
|
||||
_registry.register_defaults()
|
||||
|
||||
|
||||
def reset_parser_registry() -> None:
|
||||
"""Reset the module-level registry state to its initial values.
|
||||
|
||||
Resets _registry and _discovery_complete so the next call to
|
||||
get_parser_registry will re-initialise everything from scratch.
|
||||
|
||||
FOR TESTS ONLY. Do not call this in production code — resetting the
|
||||
registry mid-request causes all subsequent parser lookups to go through
|
||||
discovery again, which is expensive and may have unexpected side effects
|
||||
in multi-threaded environments.
|
||||
|
||||
Returns
|
||||
-------
|
||||
None
|
||||
"""
|
||||
global _registry, _discovery_complete
|
||||
|
||||
_registry = None
|
||||
_discovery_complete = False
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Registry class
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class ParserRegistry:
|
||||
"""Registry that maps MIME types to the best available parser class.
|
||||
|
||||
Parsers are partitioned into two lists:
|
||||
|
||||
_builtins
|
||||
Parser classes registered via register_builtin (populated by
|
||||
register_defaults in Phase 3+).
|
||||
|
||||
_external
|
||||
Parser classes loaded from installed Python entrypoints via discover.
|
||||
|
||||
When resolving a parser for a file, external parsers are evaluated
|
||||
alongside built-in parsers using a uniform scoring mechanism. Both lists
|
||||
are iterated together; the class with the highest score wins. If an
|
||||
external parser wins, its attribution details are logged so users can
|
||||
identify which third-party package handled their document.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._external: list[type[ParserProtocol]] = []
|
||||
self._builtins: list[type[ParserProtocol]] = []
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Registration
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def register_builtin(self, parser_class: type[ParserProtocol]) -> None:
|
||||
"""Register a built-in parser class.
|
||||
|
||||
Built-in parsers are shipped with Paperless-ngx and are appended to
|
||||
the _builtins list. They are never overridden by external parsers;
|
||||
instead, scoring determines which parser wins for any given file.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
parser_class:
|
||||
The parser class to register. Must satisfy ParserProtocol.
|
||||
"""
|
||||
self._builtins.append(parser_class)
|
||||
|
||||
def register_defaults(self) -> None:
|
||||
"""Register the built-in parsers that ship with Paperless-ngx.
|
||||
|
||||
Each parser that has been migrated to the new ParserProtocol interface
|
||||
is registered here. Parsers are added in ascending weight order so
|
||||
that log output is predictable; scoring determines which parser wins
|
||||
at runtime regardless of registration order.
|
||||
"""
|
||||
from paperless.parsers.text import TextDocumentParser
|
||||
|
||||
self.register_builtin(TextDocumentParser)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Discovery
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def discover(self) -> None:
|
||||
"""Load third-party parsers from the "paperless_ngx.parsers" entrypoint group.
|
||||
|
||||
For each advertised entrypoint the method:
|
||||
|
||||
1. Calls ep.load() to import the class.
|
||||
2. Validates that the class exposes all required attributes.
|
||||
3. On success, appends the class to _external and logs an info message.
|
||||
4. On failure (import error or missing attributes), logs an appropriate
|
||||
warning/error and continues to the next entrypoint.
|
||||
|
||||
Errors during discovery of a single parser do not prevent other parsers
|
||||
from being loaded.
|
||||
|
||||
Returns
|
||||
-------
|
||||
None
|
||||
"""
|
||||
eps = entry_points(group="paperless_ngx.parsers")
|
||||
|
||||
for ep in eps:
|
||||
try:
|
||||
parser_class = ep.load()
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"Failed to load parser entrypoint '%s' — skipping.",
|
||||
ep.name,
|
||||
)
|
||||
continue
|
||||
|
||||
missing = [
|
||||
attr for attr in _REQUIRED_ATTRS if not hasattr(parser_class, attr)
|
||||
]
|
||||
if missing:
|
||||
logger.warning(
|
||||
"Parser loaded from entrypoint '%s' is missing required "
|
||||
"attributes %r — skipping.",
|
||||
ep.name,
|
||||
missing,
|
||||
)
|
||||
continue
|
||||
|
||||
self._external.append(parser_class)
|
||||
logger.info(
|
||||
"Loaded third-party parser '%s' v%s by %s (entrypoint: '%s').",
|
||||
parser_class.name,
|
||||
parser_class.version,
|
||||
parser_class.author,
|
||||
ep.name,
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Summary logging
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def log_summary(self) -> None:
|
||||
"""Log a startup summary of all registered parsers.
|
||||
|
||||
Built-in parsers are listed first, followed by any external parsers
|
||||
discovered from entrypoints. If no external parsers were found a
|
||||
short informational message is logged instead of an empty list.
|
||||
|
||||
Returns
|
||||
-------
|
||||
None
|
||||
"""
|
||||
logger.info(
|
||||
"Built-in parsers (%d):",
|
||||
len(self._builtins),
|
||||
)
|
||||
for cls in self._builtins:
|
||||
logger.info(
|
||||
" [built-in] %s v%s — %s",
|
||||
getattr(cls, "name", repr(cls)),
|
||||
getattr(cls, "version", "unknown"),
|
||||
getattr(cls, "url", "built-in"),
|
||||
)
|
||||
|
||||
if not self._external:
|
||||
logger.info("No third-party parsers discovered.")
|
||||
return
|
||||
|
||||
logger.info(
|
||||
"Third-party parsers (%d):",
|
||||
len(self._external),
|
||||
)
|
||||
for cls in self._external:
|
||||
logger.info(
|
||||
" [external] %s v%s by %s — report issues at %s",
|
||||
getattr(cls, "name", repr(cls)),
|
||||
getattr(cls, "version", "unknown"),
|
||||
getattr(cls, "author", "unknown"),
|
||||
getattr(cls, "url", "unknown"),
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Parser resolution
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def get_parser_for_file(
|
||||
self,
|
||||
mime_type: str,
|
||||
filename: str,
|
||||
path: Path | None = None,
|
||||
) -> type[ParserProtocol] | None:
|
||||
"""Return the best parser class for the given file, or None.
|
||||
|
||||
All registered parsers (external first, then built-ins) are evaluated
|
||||
against the file. A parser is eligible if mime_type appears in the dict
|
||||
returned by its supported_mime_types classmethod, and its score
|
||||
classmethod returns a non-None integer.
|
||||
|
||||
The parser with the highest score wins. When two parsers return the
|
||||
same score, the one that appears earlier in the evaluation order wins
|
||||
(external parsers are evaluated before built-ins, giving third-party
|
||||
packages a chance to override defaults at equal priority).
|
||||
|
||||
When an external parser is selected, its identity is logged at INFO
|
||||
level so operators can trace which package handled a document.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mime_type:
|
||||
The detected MIME type of the file.
|
||||
filename:
|
||||
The original filename, including extension.
|
||||
path:
|
||||
Optional filesystem path to the file. Forwarded to each
|
||||
parser's score method.
|
||||
|
||||
Returns
|
||||
-------
|
||||
type[ParserProtocol] | None
|
||||
The winning parser class, or None if no parser can handle the file.
|
||||
"""
|
||||
best_score: int | None = None
|
||||
best_parser: type[ParserProtocol] | None = None
|
||||
|
||||
# External parsers are placed first so that, at equal scores, an
|
||||
# external parser wins over a built-in (first-seen policy).
|
||||
for parser_class in (*self._external, *self._builtins):
|
||||
if mime_type not in parser_class.supported_mime_types():
|
||||
continue
|
||||
|
||||
score = parser_class.score(mime_type, filename, path)
|
||||
if score is None:
|
||||
continue
|
||||
|
||||
if best_score is None or score > best_score:
|
||||
best_score = score
|
||||
best_parser = parser_class
|
||||
|
||||
if best_parser is not None and best_parser in self._external:
|
||||
logger.info(
|
||||
"Document handled by third-party parser '%s' v%s — %s",
|
||||
getattr(best_parser, "name", repr(best_parser)),
|
||||
getattr(best_parser, "version", "unknown"),
|
||||
getattr(best_parser, "url", "unknown"),
|
||||
)
|
||||
|
||||
return best_parser
|
||||
320
src/paperless/parsers/text.py
Normal file
320
src/paperless/parsers/text.py
Normal file
@@ -0,0 +1,320 @@
|
||||
"""
|
||||
Built-in plain-text document parser.
|
||||
|
||||
Handles text/plain, text/csv, and application/csv MIME types by reading the
|
||||
file content directly. Thumbnails are generated by rendering a page-sized
|
||||
WebP image from the first 100,000 characters using Pillow.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import shutil
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
from typing import Self
|
||||
|
||||
from django.conf import settings
|
||||
from PIL import Image
|
||||
from PIL import ImageDraw
|
||||
from PIL import ImageFont
|
||||
|
||||
from paperless.version import __full_version_str__
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import datetime
|
||||
from types import TracebackType
|
||||
|
||||
from paperless.parsers import MetadataEntry
|
||||
|
||||
logger = logging.getLogger("paperless.parsing.text")
|
||||
|
||||
_SUPPORTED_MIME_TYPES: dict[str, str] = {
|
||||
"text/plain": ".txt",
|
||||
"text/csv": ".csv",
|
||||
"application/csv": ".csv",
|
||||
}
|
||||
|
||||
|
||||
class TextDocumentParser:
|
||||
"""Parse plain-text documents (txt, csv) for Paperless-ngx.
|
||||
|
||||
This parser reads the file content directly as UTF-8 text and renders a
|
||||
simple thumbnail using Pillow. It does not perform OCR and does not
|
||||
produce a searchable PDF archive copy.
|
||||
|
||||
Class attributes
|
||||
----------------
|
||||
name : str
|
||||
Human-readable parser name.
|
||||
version : str
|
||||
Semantic version string, kept in sync with Paperless-ngx releases.
|
||||
author : str
|
||||
Maintainer name.
|
||||
url : str
|
||||
Issue tracker / source URL.
|
||||
"""
|
||||
|
||||
name: str = "Paperless-ngx Text Parser"
|
||||
version: str = __full_version_str__
|
||||
author: str = "Paperless-ngx Contributors"
|
||||
url: str = "https://github.com/paperless-ngx/paperless-ngx"
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Class methods
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls) -> dict[str, str]:
|
||||
"""Return the MIME types this parser handles.
|
||||
|
||||
Returns
|
||||
-------
|
||||
dict[str, str]
|
||||
Mapping of MIME type to preferred file extension.
|
||||
"""
|
||||
return _SUPPORTED_MIME_TYPES
|
||||
|
||||
@classmethod
|
||||
def score(
|
||||
cls,
|
||||
mime_type: str,
|
||||
filename: str,
|
||||
path: Path | None = None,
|
||||
) -> int | None:
|
||||
"""Return the priority score for handling this file.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mime_type:
|
||||
Detected MIME type of the file.
|
||||
filename:
|
||||
Original filename including extension.
|
||||
path:
|
||||
Optional filesystem path. Not inspected by this parser.
|
||||
|
||||
Returns
|
||||
-------
|
||||
int | None
|
||||
10 if the MIME type is supported, otherwise None.
|
||||
"""
|
||||
if mime_type in _SUPPORTED_MIME_TYPES:
|
||||
return 10
|
||||
return None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Properties
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@property
|
||||
def can_produce_archive(self) -> bool:
|
||||
"""Whether this parser can produce a searchable PDF archive copy.
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
Always False — the text parser does not produce a PDF archive.
|
||||
"""
|
||||
return False
|
||||
|
||||
@property
|
||||
def requires_pdf_rendition(self) -> bool:
|
||||
"""Whether the parser must produce a PDF for the frontend to display.
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
Always False — plain text files are displayable as-is.
|
||||
"""
|
||||
return False
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Lifecycle
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def __init__(self, logging_group: object = None) -> None:
|
||||
settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
|
||||
self._tempdir = Path(
|
||||
tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR),
|
||||
)
|
||||
self._text: str | None = None
|
||||
|
||||
def __enter__(self) -> Self:
|
||||
return self
|
||||
|
||||
def __exit__(
|
||||
self,
|
||||
exc_type: type[BaseException] | None,
|
||||
exc_val: BaseException | None,
|
||||
exc_tb: TracebackType | None,
|
||||
) -> None:
|
||||
logger.debug("Cleaning up temporary directory %s", self._tempdir)
|
||||
shutil.rmtree(self._tempdir, ignore_errors=True)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Core parsing interface
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def parse(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
*,
|
||||
produce_archive: bool = True,
|
||||
) -> None:
|
||||
"""Read the document and store its text content.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the text file.
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
produce_archive:
|
||||
Ignored — this parser never produces a PDF archive.
|
||||
|
||||
Raises
|
||||
------
|
||||
documents.parsers.ParseError
|
||||
If the file cannot be read.
|
||||
"""
|
||||
self._text = self._read_text(document_path)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Result accessors
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def get_text(self) -> str | None:
|
||||
"""Return the plain-text content extracted during parse.
|
||||
|
||||
Returns
|
||||
-------
|
||||
str | None
|
||||
Extracted text, or None if parse has not been called yet.
|
||||
"""
|
||||
return self._text
|
||||
|
||||
def get_date(self) -> datetime.datetime | None:
|
||||
"""Return the document date detected during parse.
|
||||
|
||||
Returns
|
||||
-------
|
||||
datetime.datetime | None
|
||||
Always None — the text parser does not detect dates.
|
||||
"""
|
||||
return None
|
||||
|
||||
def get_archive_path(self) -> Path | None:
|
||||
"""Return the path to a generated archive PDF, or None.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path | None
|
||||
Always None — the text parser does not produce a PDF archive.
|
||||
"""
|
||||
return None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Thumbnail and metadata
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
|
||||
"""Render the first portion of the document as a WebP thumbnail.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the source document.
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Path to the generated WebP thumbnail inside the temporary directory.
|
||||
"""
|
||||
max_chars = 100_000
|
||||
file_size_limit = 50 * 1024 * 1024
|
||||
|
||||
if document_path.stat().st_size > file_size_limit:
|
||||
text = "[File too large to preview]"
|
||||
else:
|
||||
with Path(document_path).open("r", encoding="utf-8", errors="replace") as f:
|
||||
text = f.read(max_chars)
|
||||
|
||||
img = Image.new("RGB", (500, 700), color="white")
|
||||
draw = ImageDraw.Draw(img)
|
||||
font = ImageFont.truetype(
|
||||
font=settings.THUMBNAIL_FONT_NAME,
|
||||
size=20,
|
||||
layout_engine=ImageFont.Layout.BASIC,
|
||||
)
|
||||
draw.multiline_text((5, 5), text, font=font, fill="black", spacing=4)
|
||||
|
||||
out_path = self._tempdir / "thumb.webp"
|
||||
img.save(out_path, format="WEBP")
|
||||
|
||||
return out_path
|
||||
|
||||
def get_page_count(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> int | None:
|
||||
"""Return the number of pages in the document.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the source document.
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
|
||||
Returns
|
||||
-------
|
||||
int | None
|
||||
Always None — page count is not meaningful for plain text.
|
||||
"""
|
||||
return None
|
||||
|
||||
def extract_metadata(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> list[MetadataEntry]:
|
||||
"""Extract format-specific metadata from the document.
|
||||
|
||||
Returns
|
||||
-------
|
||||
list[MetadataEntry]
|
||||
Always ``[]`` — plain text files carry no structured metadata.
|
||||
"""
|
||||
return []
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Private helpers
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _read_text(self, filepath: Path) -> str:
|
||||
"""Read file content, replacing invalid UTF-8 bytes rather than failing.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
filepath:
|
||||
Path to the file to read.
|
||||
|
||||
Returns
|
||||
-------
|
||||
str
|
||||
File content as a string.
|
||||
"""
|
||||
try:
|
||||
return filepath.read_text(encoding="utf-8")
|
||||
except UnicodeDecodeError as exc:
|
||||
logger.warning(
|
||||
"Unicode error reading %s, replacing bad bytes: %s",
|
||||
filepath,
|
||||
exc,
|
||||
)
|
||||
return filepath.read_bytes().decode("utf-8", errors="replace")
|
||||
440
src/paperless/parsers/tika.py
Normal file
440
src/paperless/parsers/tika.py
Normal file
@@ -0,0 +1,440 @@
|
||||
"""
|
||||
Built-in Tika document parser.
|
||||
|
||||
Handles Office documents (DOCX, ODT, XLS, XLSX, PPT, PPTX, RTF, etc.) by
|
||||
sending them to an Apache Tika server for text extraction and a Gotenberg
|
||||
server for PDF conversion. Because the source formats cannot be rendered by
|
||||
a browser natively, the parser always produces a PDF rendition for display.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import shutil
|
||||
import tempfile
|
||||
from contextlib import ExitStack
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
from typing import Self
|
||||
|
||||
import httpx
|
||||
from django.conf import settings
|
||||
from django.utils import timezone
|
||||
from gotenberg_client import GotenbergClient
|
||||
from gotenberg_client.options import PdfAFormat
|
||||
from tika_client import TikaClient
|
||||
|
||||
from documents.parsers import ParseError
|
||||
from documents.parsers import make_thumbnail_from_pdf
|
||||
from paperless.config import OutputTypeConfig
|
||||
from paperless.models import OutputTypeChoices
|
||||
from paperless.version import __full_version_str__
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import datetime
|
||||
from types import TracebackType
|
||||
|
||||
from paperless.parsers import MetadataEntry
|
||||
|
||||
logger = logging.getLogger("paperless.parsing.tika")
|
||||
|
||||
_SUPPORTED_MIME_TYPES: dict[str, str] = {
|
||||
"application/msword": ".doc",
|
||||
"application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
|
||||
"application/vnd.ms-excel": ".xls",
|
||||
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
|
||||
"application/vnd.ms-powerpoint": ".ppt",
|
||||
"application/vnd.openxmlformats-officedocument.presentationml.presentation": ".pptx",
|
||||
"application/vnd.openxmlformats-officedocument.presentationml.slideshow": ".ppsx",
|
||||
"application/vnd.oasis.opendocument.presentation": ".odp",
|
||||
"application/vnd.oasis.opendocument.spreadsheet": ".ods",
|
||||
"application/vnd.oasis.opendocument.text": ".odt",
|
||||
"application/vnd.oasis.opendocument.graphics": ".odg",
|
||||
"text/rtf": ".rtf",
|
||||
}
|
||||
|
||||
|
||||
class TikaDocumentParser:
|
||||
"""Parse Office documents via Apache Tika and Gotenberg for Paperless-ngx.
|
||||
|
||||
Text extraction is handled by the Tika server. PDF conversion for display
|
||||
is handled by Gotenberg (LibreOffice route). Because the source formats
|
||||
cannot be rendered by a browser natively, ``requires_pdf_rendition`` is
|
||||
True and the PDF is always produced regardless of the ``produce_archive``
|
||||
flag passed to ``parse``.
|
||||
|
||||
Both ``TikaClient`` and ``GotenbergClient`` are opened once in
|
||||
``__enter__`` via an ``ExitStack`` and shared across ``parse``,
|
||||
``extract_metadata``, and ``_convert_to_pdf`` calls, then closed via
|
||||
``ExitStack.close()`` in ``__exit__``. The parser must always be used
|
||||
as a context manager.
|
||||
|
||||
Class attributes
|
||||
----------------
|
||||
name : str
|
||||
Human-readable parser name.
|
||||
version : str
|
||||
Semantic version string, kept in sync with Paperless-ngx releases.
|
||||
author : str
|
||||
Maintainer name.
|
||||
url : str
|
||||
Issue tracker / source URL.
|
||||
"""
|
||||
|
||||
name: str = "Paperless-ngx Tika Parser"
|
||||
version: str = __full_version_str__
|
||||
author: str = "Paperless-ngx Contributors"
|
||||
url: str = "https://github.com/paperless-ngx/paperless-ngx"
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Class methods
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls) -> dict[str, str]:
|
||||
"""Return the MIME types this parser handles.
|
||||
|
||||
Returns
|
||||
-------
|
||||
dict[str, str]
|
||||
Mapping of MIME type to preferred file extension.
|
||||
"""
|
||||
return _SUPPORTED_MIME_TYPES
|
||||
|
||||
@classmethod
|
||||
def score(
|
||||
cls,
|
||||
mime_type: str,
|
||||
filename: str,
|
||||
path: Path | None = None,
|
||||
) -> int | None:
|
||||
"""Return the priority score for handling this file.
|
||||
|
||||
Returns ``None`` when Tika integration is disabled so the registry
|
||||
skips this parser entirely.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mime_type:
|
||||
Detected MIME type of the file.
|
||||
filename:
|
||||
Original filename including extension.
|
||||
path:
|
||||
Optional filesystem path. Not inspected by this parser.
|
||||
|
||||
Returns
|
||||
-------
|
||||
int | None
|
||||
10 if TIKA_ENABLED and the MIME type is supported, otherwise None.
|
||||
"""
|
||||
if not settings.TIKA_ENABLED:
|
||||
return None
|
||||
if mime_type in _SUPPORTED_MIME_TYPES:
|
||||
return 10
|
||||
return None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Properties
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@property
|
||||
def can_produce_archive(self) -> bool:
|
||||
"""Whether this parser can produce a searchable PDF archive copy.
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
Always False — Tika produces a display PDF, not an OCR archive.
|
||||
"""
|
||||
return False
|
||||
|
||||
@property
|
||||
def requires_pdf_rendition(self) -> bool:
|
||||
"""Whether the parser must produce a PDF for the frontend to display.
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
Always True — Office formats cannot be rendered natively in a
|
||||
browser, so a PDF conversion is always required for display.
|
||||
"""
|
||||
return True
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Lifecycle
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def __init__(self, logging_group: object = None) -> None:
|
||||
settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
|
||||
self._tempdir = Path(
|
||||
tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR),
|
||||
)
|
||||
self._text: str | None = None
|
||||
self._date: datetime.datetime | None = None
|
||||
self._archive_path: Path | None = None
|
||||
self._exit_stack = ExitStack()
|
||||
self._tika_client: TikaClient | None = None
|
||||
self._gotenberg_client: GotenbergClient | None = None
|
||||
|
||||
def __enter__(self) -> Self:
|
||||
self._tika_client = self._exit_stack.enter_context(
|
||||
TikaClient(
|
||||
tika_url=settings.TIKA_ENDPOINT,
|
||||
timeout=settings.CELERY_TASK_TIME_LIMIT,
|
||||
),
|
||||
)
|
||||
self._gotenberg_client = self._exit_stack.enter_context(
|
||||
GotenbergClient(
|
||||
host=settings.TIKA_GOTENBERG_ENDPOINT,
|
||||
timeout=settings.CELERY_TASK_TIME_LIMIT,
|
||||
),
|
||||
)
|
||||
return self
|
||||
|
||||
def __exit__(
|
||||
self,
|
||||
exc_type: type[BaseException] | None,
|
||||
exc_val: BaseException | None,
|
||||
exc_tb: TracebackType | None,
|
||||
) -> None:
|
||||
self._exit_stack.close()
|
||||
logger.debug("Cleaning up temporary directory %s", self._tempdir)
|
||||
shutil.rmtree(self._tempdir, ignore_errors=True)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Core parsing interface
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def parse(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
*,
|
||||
produce_archive: bool = True,
|
||||
) -> None:
|
||||
"""Send the document to Tika for text extraction and Gotenberg for PDF.
|
||||
|
||||
Because ``requires_pdf_rendition`` is True the PDF conversion is
|
||||
always performed — the ``produce_archive`` flag is intentionally
|
||||
ignored.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the document file to parse.
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
produce_archive:
|
||||
Accepted for protocol compatibility but ignored; the PDF rendition
|
||||
is always produced since the source format cannot be displayed
|
||||
natively in the browser.
|
||||
|
||||
Raises
|
||||
------
|
||||
documents.parsers.ParseError
|
||||
If Tika or Gotenberg returns an error.
|
||||
"""
|
||||
if TYPE_CHECKING:
|
||||
assert self._tika_client is not None
|
||||
|
||||
logger.info("Sending %s to Tika server", document_path)
|
||||
|
||||
try:
|
||||
try:
|
||||
parsed = self._tika_client.tika.as_text.from_file(
|
||||
document_path,
|
||||
mime_type,
|
||||
)
|
||||
except httpx.HTTPStatusError as err:
|
||||
# Workaround https://issues.apache.org/jira/browse/TIKA-4110
|
||||
# Tika fails with some files as multi-part form data
|
||||
if err.response.status_code == httpx.codes.INTERNAL_SERVER_ERROR:
|
||||
parsed = self._tika_client.tika.as_text.from_buffer(
|
||||
document_path.read_bytes(),
|
||||
mime_type,
|
||||
)
|
||||
else: # pragma: no cover
|
||||
raise
|
||||
except Exception as err:
|
||||
raise ParseError(
|
||||
f"Could not parse {document_path} with tika server at "
|
||||
f"{settings.TIKA_ENDPOINT}: {err}",
|
||||
) from err
|
||||
|
||||
self._text = parsed.content
|
||||
if self._text is not None:
|
||||
self._text = self._text.strip()
|
||||
|
||||
self._date = parsed.created
|
||||
if self._date is not None and timezone.is_naive(self._date):
|
||||
self._date = timezone.make_aware(self._date)
|
||||
|
||||
# Always convert — requires_pdf_rendition=True means the browser
|
||||
# cannot display the source format natively.
|
||||
self._archive_path = self._convert_to_pdf(document_path)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Result accessors
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def get_text(self) -> str | None:
|
||||
"""Return the plain-text content extracted during parse.
|
||||
|
||||
Returns
|
||||
-------
|
||||
str | None
|
||||
Extracted text, or None if parse has not been called yet.
|
||||
"""
|
||||
return self._text
|
||||
|
||||
def get_date(self) -> datetime.datetime | None:
|
||||
"""Return the document date detected during parse.
|
||||
|
||||
Returns
|
||||
-------
|
||||
datetime.datetime | None
|
||||
Creation date from Tika metadata, or None if not detected.
|
||||
"""
|
||||
return self._date
|
||||
|
||||
def get_archive_path(self) -> Path | None:
|
||||
"""Return the path to the generated PDF rendition, or None.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path | None
|
||||
Path to the PDF produced by Gotenberg, or None if parse has not
|
||||
been called yet.
|
||||
"""
|
||||
return self._archive_path
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Thumbnail and metadata
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
|
||||
"""Generate a thumbnail from the PDF rendition of the document.
|
||||
|
||||
Converts the document to PDF first if not already done.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the source document.
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Path to the generated WebP thumbnail inside the temporary directory.
|
||||
"""
|
||||
if self._archive_path is None:
|
||||
self._archive_path = self._convert_to_pdf(document_path)
|
||||
return make_thumbnail_from_pdf(self._archive_path, self._tempdir)
|
||||
|
||||
def get_page_count(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> int | None:
|
||||
"""Return the number of pages in the document.
|
||||
|
||||
Returns
|
||||
-------
|
||||
int | None
|
||||
Always None — page count is not available from Tika.
|
||||
"""
|
||||
return None
|
||||
|
||||
def extract_metadata(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> list[MetadataEntry]:
|
||||
"""Extract format-specific metadata via the Tika metadata endpoint.
|
||||
|
||||
Returns
|
||||
-------
|
||||
list[MetadataEntry]
|
||||
All key/value pairs returned by Tika, or ``[]`` on error.
|
||||
"""
|
||||
if TYPE_CHECKING:
|
||||
assert self._tika_client is not None
|
||||
|
||||
try:
|
||||
parsed = self._tika_client.metadata.from_file(document_path, mime_type)
|
||||
return [
|
||||
{
|
||||
"namespace": "",
|
||||
"prefix": "",
|
||||
"key": key,
|
||||
"value": parsed.data[key],
|
||||
}
|
||||
for key in parsed.data
|
||||
]
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"Error while fetching document metadata for %s: %s",
|
||||
document_path,
|
||||
e,
|
||||
)
|
||||
return []
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Private helpers
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _convert_to_pdf(self, document_path: Path) -> Path:
|
||||
"""Convert the document to PDF using Gotenberg's LibreOffice route.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
Absolute path to the source document.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Path to the generated PDF inside the temporary directory.
|
||||
|
||||
Raises
|
||||
------
|
||||
documents.parsers.ParseError
|
||||
If Gotenberg returns an error.
|
||||
"""
|
||||
if TYPE_CHECKING:
|
||||
assert self._gotenberg_client is not None
|
||||
|
||||
pdf_path = self._tempdir / "convert.pdf"
|
||||
|
||||
logger.info("Converting %s to PDF as %s", document_path, pdf_path)
|
||||
|
||||
with self._gotenberg_client.libre_office.to_pdf() as route:
|
||||
# Set the output format of the resulting PDF.
|
||||
# OutputTypeConfig reads the database-stored ApplicationConfiguration
|
||||
# first, then falls back to the PAPERLESS_OCR_OUTPUT_TYPE env var.
|
||||
output_type = OutputTypeConfig().output_type
|
||||
if output_type in {
|
||||
OutputTypeChoices.PDF_A,
|
||||
OutputTypeChoices.PDF_A2,
|
||||
}:
|
||||
route.pdf_format(PdfAFormat.A2b)
|
||||
elif output_type == OutputTypeChoices.PDF_A1:
|
||||
logger.warning(
|
||||
"Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
|
||||
)
|
||||
route.pdf_format(PdfAFormat.A2b)
|
||||
elif output_type == OutputTypeChoices.PDF_A3:
|
||||
route.pdf_format(PdfAFormat.A3b)
|
||||
|
||||
route.convert(document_path)
|
||||
|
||||
try:
|
||||
response = route.run()
|
||||
pdf_path.write_bytes(response.content)
|
||||
return pdf_path
|
||||
except Exception as err:
|
||||
raise ParseError(
|
||||
f"Error while converting document to PDF: {err}",
|
||||
) from err
|
||||
48
src/paperless/tests/conftest.py
Normal file
48
src/paperless/tests/conftest.py
Normal file
@@ -0,0 +1,48 @@
|
||||
"""
|
||||
Fixtures defined here are available to every test module under
|
||||
src/paperless/tests/ (including sub-packages such as parsers/).
|
||||
|
||||
Session-scoped fixtures for the shared samples directory live here so
|
||||
sub-package conftest files can reference them without duplicating path logic.
|
||||
Parser-specific fixtures (concrete parser instances, format-specific sample
|
||||
files) live in paperless/tests/parsers/conftest.py.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import pytest
|
||||
|
||||
from paperless.parsers.registry import reset_parser_registry
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Generator
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def samples_dir() -> Path:
|
||||
"""Absolute path to the shared parser sample files directory.
|
||||
|
||||
Sub-package conftest files derive format-specific paths from this root,
|
||||
e.g. ``samples_dir / "text" / "test.txt"``.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Directory containing all sample documents used by parser tests.
|
||||
"""
|
||||
return (Path(__file__).parent / "samples").resolve()
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def clean_registry() -> Generator[None, None, None]:
|
||||
"""Reset the parser registry before and after every test.
|
||||
|
||||
This prevents registry state from leaking between tests that call
|
||||
get_parser_registry() or init_builtin_parsers().
|
||||
"""
|
||||
reset_parser_registry()
|
||||
yield
|
||||
reset_parser_registry()
|
||||
0
src/paperless/tests/parsers/__init__.py
Normal file
0
src/paperless/tests/parsers/__init__.py
Normal file
160
src/paperless/tests/parsers/conftest.py
Normal file
160
src/paperless/tests/parsers/conftest.py
Normal file
@@ -0,0 +1,160 @@
|
||||
"""
|
||||
Parser fixtures that are used across multiple test modules in this package
|
||||
are defined here. Format-specific sample-file fixtures are grouped by parser
|
||||
so it is easy to see which files belong to which test module.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import pytest
|
||||
|
||||
from paperless.parsers.text import TextDocumentParser
|
||||
from paperless.parsers.tika import TikaDocumentParser
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Generator
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Text parser sample files
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def text_samples_dir(samples_dir: Path) -> Path:
|
||||
"""Absolute path to the text parser sample files directory.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
``<samples_dir>/text/``
|
||||
"""
|
||||
return samples_dir / "text"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_txt_file(text_samples_dir: Path) -> Path:
|
||||
"""Path to a valid UTF-8 plain-text sample file.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Absolute path to ``text/test.txt``.
|
||||
"""
|
||||
return text_samples_dir / "test.txt"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def malformed_txt_file(text_samples_dir: Path) -> Path:
|
||||
"""Path to a text file containing invalid UTF-8 bytes.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Absolute path to ``text/decode_error.txt``.
|
||||
"""
|
||||
return text_samples_dir / "decode_error.txt"
|
||||
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Text parser instance
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def text_parser() -> Generator[TextDocumentParser, None, None]:
|
||||
"""Yield a TextDocumentParser and clean up its temporary directory afterwards.
|
||||
|
||||
Yields
|
||||
------
|
||||
TextDocumentParser
|
||||
A ready-to-use parser instance.
|
||||
"""
|
||||
with TextDocumentParser() as parser:
|
||||
yield parser
|
||||
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Tika parser sample files
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def tika_samples_dir(samples_dir: Path) -> Path:
|
||||
"""Absolute path to the Tika parser sample files directory.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
``<samples_dir>/tika/``
|
||||
"""
|
||||
return samples_dir / "tika"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_odt_file(tika_samples_dir: Path) -> Path:
|
||||
"""Path to a sample ODT file.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Absolute path to ``tika/sample.odt``.
|
||||
"""
|
||||
return tika_samples_dir / "sample.odt"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_docx_file(tika_samples_dir: Path) -> Path:
|
||||
"""Path to a sample DOCX file.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Absolute path to ``tika/sample.docx``.
|
||||
"""
|
||||
return tika_samples_dir / "sample.docx"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_doc_file(tika_samples_dir: Path) -> Path:
|
||||
"""Path to a sample DOC file.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Absolute path to ``tika/sample.doc``.
|
||||
"""
|
||||
return tika_samples_dir / "sample.doc"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_broken_odt(tika_samples_dir: Path) -> Path:
|
||||
"""Path to a broken ODT file that triggers the multi-part fallback.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Absolute path to ``tika/multi-part-broken.odt``.
|
||||
"""
|
||||
return tika_samples_dir / "multi-part-broken.odt"
|
||||
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Tika parser instance
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def tika_parser() -> Generator[TikaDocumentParser, None, None]:
|
||||
"""Yield a TikaDocumentParser and clean up its temporary directory afterwards.
|
||||
|
||||
Yields
|
||||
------
|
||||
TikaDocumentParser
|
||||
A ready-to-use parser instance.
|
||||
"""
|
||||
with TikaDocumentParser() as parser:
|
||||
yield parser
|
||||
256
src/paperless/tests/parsers/test_text_parser.py
Normal file
256
src/paperless/tests/parsers/test_text_parser.py
Normal file
@@ -0,0 +1,256 @@
|
||||
"""
|
||||
Tests for paperless.parsers.text.TextDocumentParser.
|
||||
|
||||
All tests use the context-manager protocol for parser lifecycle. Sample
|
||||
files are provided by session-scoped fixtures defined in conftest.py.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from paperless.parsers import ParserProtocol
|
||||
from paperless.parsers.text import TextDocumentParser
|
||||
|
||||
|
||||
class TestTextParserProtocol:
|
||||
"""Verify that TextDocumentParser satisfies the ParserProtocol contract."""
|
||||
|
||||
def test_isinstance_satisfies_protocol(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
) -> None:
|
||||
assert isinstance(text_parser, ParserProtocol)
|
||||
|
||||
def test_class_attributes_present(self) -> None:
|
||||
assert isinstance(TextDocumentParser.name, str) and TextDocumentParser.name
|
||||
assert (
|
||||
isinstance(TextDocumentParser.version, str) and TextDocumentParser.version
|
||||
)
|
||||
assert isinstance(TextDocumentParser.author, str) and TextDocumentParser.author
|
||||
assert isinstance(TextDocumentParser.url, str) and TextDocumentParser.url
|
||||
|
||||
def test_supported_mime_types_returns_dict(self) -> None:
|
||||
mime_types = TextDocumentParser.supported_mime_types()
|
||||
assert isinstance(mime_types, dict)
|
||||
assert "text/plain" in mime_types
|
||||
assert "text/csv" in mime_types
|
||||
assert "application/csv" in mime_types
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("mime_type", "expected"),
|
||||
[
|
||||
("text/plain", 10),
|
||||
("text/csv", 10),
|
||||
("application/csv", 10),
|
||||
("application/pdf", None),
|
||||
("image/png", None),
|
||||
],
|
||||
)
|
||||
def test_score(self, mime_type: str, expected: int | None) -> None:
|
||||
assert TextDocumentParser.score(mime_type, "file.txt") == expected
|
||||
|
||||
def test_can_produce_archive_is_false(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
) -> None:
|
||||
assert text_parser.can_produce_archive is False
|
||||
|
||||
def test_requires_pdf_rendition_is_false(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
) -> None:
|
||||
assert text_parser.requires_pdf_rendition is False
|
||||
|
||||
|
||||
class TestTextParserLifecycle:
|
||||
"""Verify context-manager behaviour and temporary directory cleanup."""
|
||||
|
||||
def test_context_manager_cleans_up_tempdir(self) -> None:
|
||||
with TextDocumentParser() as parser:
|
||||
tempdir = parser._tempdir
|
||||
assert tempdir.exists()
|
||||
assert not tempdir.exists()
|
||||
|
||||
def test_context_manager_cleans_up_after_exception(self) -> None:
|
||||
tempdir: Path | None = None
|
||||
with pytest.raises(RuntimeError):
|
||||
with TextDocumentParser() as parser:
|
||||
tempdir = parser._tempdir
|
||||
raise RuntimeError("boom")
|
||||
assert tempdir is not None
|
||||
assert not tempdir.exists()
|
||||
|
||||
|
||||
class TestTextParserParse:
|
||||
"""Verify parse() and the result accessors."""
|
||||
|
||||
def test_parse_valid_utf8(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
text_parser.parse(sample_txt_file, "text/plain")
|
||||
|
||||
assert text_parser.get_text() == "This is a test file.\n"
|
||||
|
||||
def test_parse_returns_none_for_archive_path(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
text_parser.parse(sample_txt_file, "text/plain")
|
||||
|
||||
assert text_parser.get_archive_path() is None
|
||||
|
||||
def test_parse_returns_none_for_date(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
text_parser.parse(sample_txt_file, "text/plain")
|
||||
|
||||
assert text_parser.get_date() is None
|
||||
|
||||
def test_parse_invalid_utf8_bytes_replaced(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
malformed_txt_file: Path,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A text file containing invalid UTF-8 byte sequences
|
||||
WHEN:
|
||||
- The file is parsed
|
||||
THEN:
|
||||
- Parsing succeeds
|
||||
- Invalid bytes are replaced with the Unicode replacement character
|
||||
"""
|
||||
text_parser.parse(malformed_txt_file, "text/plain")
|
||||
|
||||
assert text_parser.get_text() == "Pantothens\ufffdure\n"
|
||||
|
||||
def test_get_text_none_before_parse(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
) -> None:
|
||||
assert text_parser.get_text() is None
|
||||
|
||||
|
||||
class TestTextParserThumbnail:
|
||||
"""Verify thumbnail generation."""
|
||||
|
||||
def test_thumbnail_exists_and_is_file(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
thumb = text_parser.get_thumbnail(sample_txt_file, "text/plain")
|
||||
|
||||
assert thumb.exists()
|
||||
assert thumb.is_file()
|
||||
|
||||
def test_thumbnail_large_file_does_not_read_all(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A text file larger than 50 MB
|
||||
WHEN:
|
||||
- A thumbnail is requested
|
||||
THEN:
|
||||
- The thumbnail is generated without loading the full file
|
||||
"""
|
||||
with tempfile.NamedTemporaryFile(
|
||||
delete=False,
|
||||
mode="w",
|
||||
encoding="utf-8",
|
||||
suffix=".txt",
|
||||
) as tmp:
|
||||
tmp.write("A" * (51 * 1024 * 1024))
|
||||
large_file = Path(tmp.name)
|
||||
|
||||
try:
|
||||
thumb = text_parser.get_thumbnail(large_file, "text/plain")
|
||||
assert thumb.exists()
|
||||
assert thumb.is_file()
|
||||
finally:
|
||||
large_file.unlink(missing_ok=True)
|
||||
|
||||
def test_get_page_count_returns_none(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
assert text_parser.get_page_count(sample_txt_file, "text/plain") is None
|
||||
|
||||
|
||||
class TestTextParserMetadata:
|
||||
"""Verify extract_metadata behaviour."""
|
||||
|
||||
def test_extract_metadata_returns_empty_list(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
result = text_parser.extract_metadata(sample_txt_file, "text/plain")
|
||||
|
||||
assert result == []
|
||||
|
||||
def test_extract_metadata_returns_list_type(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
result = text_parser.extract_metadata(sample_txt_file, "text/plain")
|
||||
|
||||
assert isinstance(result, list)
|
||||
|
||||
def test_extract_metadata_ignores_mime_type(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
"""extract_metadata returns [] regardless of the mime_type argument."""
|
||||
assert text_parser.extract_metadata(sample_txt_file, "application/pdf") == []
|
||||
assert text_parser.extract_metadata(sample_txt_file, "text/csv") == []
|
||||
|
||||
|
||||
class TestTextParserRegistry:
|
||||
"""Verify that TextDocumentParser is registered by default."""
|
||||
|
||||
def test_registered_in_defaults(self) -> None:
|
||||
from paperless.parsers.registry import ParserRegistry
|
||||
|
||||
registry = ParserRegistry()
|
||||
registry.register_defaults()
|
||||
|
||||
assert TextDocumentParser in registry._builtins
|
||||
|
||||
def test_get_parser_for_text_plain(self) -> None:
|
||||
from paperless.parsers.registry import get_parser_registry
|
||||
|
||||
registry = get_parser_registry()
|
||||
parser_cls = registry.get_parser_for_file("text/plain", "doc.txt")
|
||||
|
||||
assert parser_cls is TextDocumentParser
|
||||
|
||||
def test_get_parser_for_text_csv(self) -> None:
|
||||
from paperless.parsers.registry import get_parser_registry
|
||||
|
||||
registry = get_parser_registry()
|
||||
parser_cls = registry.get_parser_for_file("text/csv", "data.csv")
|
||||
|
||||
assert parser_cls is TextDocumentParser
|
||||
|
||||
def test_get_parser_for_unknown_type_returns_none(self) -> None:
|
||||
from paperless.parsers.registry import get_parser_registry
|
||||
|
||||
registry = get_parser_registry()
|
||||
parser_cls = registry.get_parser_for_file("application/pdf", "doc.pdf")
|
||||
|
||||
assert parser_cls is None
|
||||
@@ -4,7 +4,7 @@ from pathlib import Path
|
||||
import pytest
|
||||
|
||||
from documents.tests.utils import util_call_with_backoff
|
||||
from paperless_tika.parsers import TikaDocumentParser
|
||||
from paperless.parsers.tika import TikaDocumentParser
|
||||
|
||||
|
||||
@pytest.mark.skipif(
|
||||
@@ -42,14 +42,15 @@ class TestTikaParserAgainstServer:
|
||||
)
|
||||
|
||||
assert (
|
||||
tika_parser.text
|
||||
tika_parser.get_text()
|
||||
== "This is an ODT test document, created September 14, 2022"
|
||||
)
|
||||
assert tika_parser.archive_path is not None
|
||||
assert b"PDF-" in tika_parser.archive_path.read_bytes()[:10]
|
||||
archive = tika_parser.get_archive_path()
|
||||
assert archive is not None
|
||||
assert b"PDF-" in archive.read_bytes()[:10]
|
||||
|
||||
# TODO: Unsure what can set the Creation-Date field in a document, enable when possible
|
||||
# self.assertEqual(tika_parser.date, datetime.datetime(2022, 9, 14))
|
||||
# self.assertEqual(tika_parser.get_date(), datetime.datetime(2022, 9, 14))
|
||||
|
||||
def test_basic_parse_docx(
|
||||
self,
|
||||
@@ -74,14 +75,15 @@ class TestTikaParserAgainstServer:
|
||||
)
|
||||
|
||||
assert (
|
||||
tika_parser.text
|
||||
tika_parser.get_text()
|
||||
== "This is an DOCX test document, also made September 14, 2022"
|
||||
)
|
||||
assert tika_parser.archive_path is not None
|
||||
with Path(tika_parser.archive_path).open("rb") as f:
|
||||
archive = tika_parser.get_archive_path()
|
||||
assert archive is not None
|
||||
with archive.open("rb") as f:
|
||||
assert b"PDF-" in f.read()[:10]
|
||||
|
||||
# self.assertEqual(tika_parser.date, datetime.datetime(2022, 9, 14))
|
||||
# self.assertEqual(tika_parser.get_date(), datetime.datetime(2022, 9, 14))
|
||||
|
||||
def test_basic_parse_doc(
|
||||
self,
|
||||
@@ -102,13 +104,12 @@ class TestTikaParserAgainstServer:
|
||||
[sample_doc_file, "application/msword"],
|
||||
)
|
||||
|
||||
assert tika_parser.text is not None
|
||||
assert (
|
||||
"This is a test document, saved in the older .doc format"
|
||||
in tika_parser.text
|
||||
)
|
||||
assert tika_parser.archive_path is not None
|
||||
with Path(tika_parser.archive_path).open("rb") as f:
|
||||
text = tika_parser.get_text()
|
||||
assert text is not None
|
||||
assert "This is a test document, saved in the older .doc format" in text
|
||||
archive = tika_parser.get_archive_path()
|
||||
assert archive is not None
|
||||
with archive.open("rb") as f:
|
||||
assert b"PDF-" in f.read()[:10]
|
||||
|
||||
def test_tika_fails_multi_part(
|
||||
@@ -133,6 +134,7 @@ class TestTikaParserAgainstServer:
|
||||
[sample_broken_odt, "application/vnd.oasis.opendocument.text"],
|
||||
)
|
||||
|
||||
assert tika_parser.archive_path is not None
|
||||
with Path(tika_parser.archive_path).open("rb") as f:
|
||||
archive = tika_parser.get_archive_path()
|
||||
assert archive is not None
|
||||
with archive.open("rb") as f:
|
||||
assert b"PDF-" in f.read()[:10]
|
||||
@@ -9,7 +9,56 @@ from pytest_django.fixtures import SettingsWrapper
|
||||
from pytest_httpx import HTTPXMock
|
||||
|
||||
from documents.parsers import ParseError
|
||||
from paperless_tika.parsers import TikaDocumentParser
|
||||
from paperless.parsers import ParserProtocol
|
||||
from paperless.parsers.tika import TikaDocumentParser
|
||||
|
||||
|
||||
class TestTikaParserRegistryInterface:
|
||||
"""Verify that TikaDocumentParser satisfies the ParserProtocol contract."""
|
||||
|
||||
def test_satisfies_parser_protocol(self) -> None:
|
||||
assert isinstance(TikaDocumentParser(), ParserProtocol)
|
||||
|
||||
def test_supported_mime_types_is_classmethod(self) -> None:
|
||||
mime_types = TikaDocumentParser.supported_mime_types()
|
||||
assert isinstance(mime_types, dict)
|
||||
assert len(mime_types) > 0
|
||||
|
||||
def test_score_returns_none_when_tika_disabled(
|
||||
self,
|
||||
settings: SettingsWrapper,
|
||||
) -> None:
|
||||
settings.TIKA_ENABLED = False
|
||||
result = TikaDocumentParser.score(
|
||||
"application/vnd.oasis.opendocument.text",
|
||||
"sample.odt",
|
||||
)
|
||||
assert result is None
|
||||
|
||||
def test_score_returns_int_when_tika_enabled(
|
||||
self,
|
||||
settings: SettingsWrapper,
|
||||
) -> None:
|
||||
settings.TIKA_ENABLED = True
|
||||
result = TikaDocumentParser.score(
|
||||
"application/vnd.oasis.opendocument.text",
|
||||
"sample.odt",
|
||||
)
|
||||
assert isinstance(result, int)
|
||||
|
||||
def test_score_returns_none_for_unsupported_mime(
|
||||
self,
|
||||
settings: SettingsWrapper,
|
||||
) -> None:
|
||||
settings.TIKA_ENABLED = True
|
||||
result = TikaDocumentParser.score("application/pdf", "doc.pdf")
|
||||
assert result is None
|
||||
|
||||
def test_can_produce_archive_is_false(self) -> None:
|
||||
assert TikaDocumentParser().can_produce_archive is False
|
||||
|
||||
def test_requires_pdf_rendition_is_true(self) -> None:
|
||||
assert TikaDocumentParser().requires_pdf_rendition is True
|
||||
|
||||
|
||||
@pytest.mark.django_db()
|
||||
@@ -36,12 +85,12 @@ class TestTikaParser:
|
||||
|
||||
tika_parser.parse(sample_odt_file, "application/vnd.oasis.opendocument.text")
|
||||
|
||||
assert tika_parser.text == "the content"
|
||||
assert tika_parser.archive_path is not None
|
||||
with Path(tika_parser.archive_path).open("rb") as f:
|
||||
assert tika_parser.get_text() == "the content"
|
||||
assert tika_parser.get_archive_path() is not None
|
||||
with Path(tika_parser.get_archive_path()).open("rb") as f:
|
||||
assert f.read() == b"PDF document"
|
||||
|
||||
assert tika_parser.date == datetime.datetime(
|
||||
assert tika_parser.get_date() == datetime.datetime(
|
||||
2020,
|
||||
11,
|
||||
21,
|
||||
@@ -89,7 +138,7 @@ class TestTikaParser:
|
||||
httpx_mock.add_response(status_code=HTTPStatus.INTERNAL_SERVER_ERROR)
|
||||
|
||||
with pytest.raises(ParseError):
|
||||
tika_parser.convert_to_pdf(sample_odt_file, None)
|
||||
tika_parser._convert_to_pdf(sample_odt_file)
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("setting_value", "expected_form_value"),
|
||||
@@ -106,7 +155,6 @@ class TestTikaParser:
|
||||
expected_form_value: str,
|
||||
httpx_mock: HTTPXMock,
|
||||
settings: SettingsWrapper,
|
||||
tika_parser: TikaDocumentParser,
|
||||
sample_odt_file: Path,
|
||||
) -> None:
|
||||
"""
|
||||
@@ -117,6 +165,8 @@ class TestTikaParser:
|
||||
THEN:
|
||||
- Request to Gotenberg contains the expected PDF/A format string
|
||||
"""
|
||||
# Parser must be created after the setting is changed so that
|
||||
# OutputTypeConfig reads the correct value at __init__ time.
|
||||
settings.OCR_OUTPUT_TYPE = setting_value
|
||||
httpx_mock.add_response(
|
||||
status_code=codes.OK,
|
||||
@@ -124,7 +174,8 @@ class TestTikaParser:
|
||||
method="POST",
|
||||
)
|
||||
|
||||
tika_parser.convert_to_pdf(sample_odt_file, None)
|
||||
with TikaDocumentParser() as parser:
|
||||
parser._convert_to_pdf(sample_odt_file)
|
||||
|
||||
request = httpx_mock.get_request()
|
||||
|
||||
714
src/paperless/tests/test_registry.py
Normal file
714
src/paperless/tests/test_registry.py
Normal file
@@ -0,0 +1,714 @@
|
||||
"""
|
||||
Tests for :mod:`paperless.parsers` (ParserProtocol) and
|
||||
:mod:`paperless.parsers.registry` (ParserRegistry + module-level helpers).
|
||||
|
||||
All tests use pytest-style functions/classes — no unittest.TestCase.
|
||||
The ``clean_registry`` fixture ensures complete isolation between tests by
|
||||
resetting the module-level singleton before and after every test.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from importlib.metadata import EntryPoint
|
||||
from pathlib import Path
|
||||
from typing import Self
|
||||
from unittest.mock import MagicMock
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
from paperless.parsers import ParserProtocol
|
||||
from paperless.parsers.registry import ParserRegistry
|
||||
from paperless.parsers.registry import get_parser_registry
|
||||
from paperless.parsers.registry import init_builtin_parsers
|
||||
from paperless.parsers.registry import reset_parser_registry
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def dummy_parser_cls() -> type:
|
||||
"""Return a class that fully satisfies :class:`ParserProtocol`.
|
||||
|
||||
GIVEN: A need to exercise registry and Protocol logic with a minimal
|
||||
but complete parser.
|
||||
WHEN: A test requests this fixture.
|
||||
THEN: A class with all required attributes and methods is returned.
|
||||
"""
|
||||
|
||||
class DummyParser:
|
||||
name = "dummy-parser"
|
||||
version = "0.1.0"
|
||||
author = "Test Author"
|
||||
url = "https://example.com/dummy-parser"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls) -> dict[str, str]:
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(
|
||||
cls,
|
||||
mime_type: str,
|
||||
filename: str,
|
||||
path: Path | None = None,
|
||||
) -> int | None:
|
||||
return 10
|
||||
|
||||
@property
|
||||
def can_produce_archive(self) -> bool:
|
||||
return False
|
||||
|
||||
@property
|
||||
def requires_pdf_rendition(self) -> bool:
|
||||
return False
|
||||
|
||||
def parse(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
*,
|
||||
produce_archive: bool = True,
|
||||
) -> None:
|
||||
"""
|
||||
Required to exist, but doesn't need to do anything
|
||||
"""
|
||||
|
||||
def get_text(self) -> str | None:
|
||||
return None
|
||||
|
||||
def get_date(self) -> None:
|
||||
return None
|
||||
|
||||
def get_archive_path(self) -> Path | None:
|
||||
return None
|
||||
|
||||
def get_thumbnail(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> Path:
|
||||
return Path("/tmp/thumbnail.webp")
|
||||
|
||||
def get_page_count(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> int | None:
|
||||
return None
|
||||
|
||||
def extract_metadata(
|
||||
self,
|
||||
document_path: Path,
|
||||
mime_type: str,
|
||||
) -> list:
|
||||
return []
|
||||
|
||||
def __enter__(self) -> Self:
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type, exc_val, exc_tb) -> None:
|
||||
"""
|
||||
Required to exist, but doesn't need to do anything
|
||||
"""
|
||||
|
||||
return DummyParser
|
||||
|
||||
|
||||
class TestParserProtocol:
|
||||
"""Verify runtime isinstance() checks against ParserProtocol."""
|
||||
|
||||
def test_compliant_class_instance_passes_isinstance(
|
||||
self,
|
||||
dummy_parser_cls: type,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A class that implements every method required by ParserProtocol.
|
||||
WHEN: isinstance() is called with the Protocol.
|
||||
THEN: The check passes (returns True).
|
||||
"""
|
||||
instance = dummy_parser_cls()
|
||||
assert isinstance(instance, ParserProtocol)
|
||||
|
||||
def test_non_compliant_class_instance_fails_isinstance(self) -> None:
|
||||
"""
|
||||
GIVEN: A plain class with no parser-related methods.
|
||||
WHEN: isinstance() is called with ParserProtocol.
|
||||
THEN: The check fails (returns False).
|
||||
"""
|
||||
|
||||
class Unrelated:
|
||||
pass
|
||||
|
||||
assert not isinstance(Unrelated(), ParserProtocol)
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"missing_method",
|
||||
[
|
||||
pytest.param("parse", id="missing-parse"),
|
||||
pytest.param("get_text", id="missing-get_text"),
|
||||
pytest.param("get_thumbnail", id="missing-get_thumbnail"),
|
||||
pytest.param("__enter__", id="missing-__enter__"),
|
||||
pytest.param("__exit__", id="missing-__exit__"),
|
||||
],
|
||||
)
|
||||
def test_partial_compliant_fails_isinstance(
|
||||
self,
|
||||
dummy_parser_cls: type,
|
||||
missing_method: str,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A class that satisfies ParserProtocol except for one method.
|
||||
WHEN: isinstance() is called with ParserProtocol.
|
||||
THEN: The check fails because the Protocol is not fully satisfied.
|
||||
"""
|
||||
# Create a subclass and delete the specified method to break compliance.
|
||||
partial_cls = type(
|
||||
"PartialParser",
|
||||
(dummy_parser_cls,),
|
||||
{missing_method: None}, # Replace with None — not callable
|
||||
)
|
||||
assert not isinstance(partial_cls(), ParserProtocol)
|
||||
|
||||
|
||||
class TestRegistrySingleton:
|
||||
"""Verify the module-level singleton lifecycle functions."""
|
||||
|
||||
def test_get_parser_registry_returns_instance(self) -> None:
|
||||
"""
|
||||
GIVEN: No registry has been created yet.
|
||||
WHEN: get_parser_registry() is called.
|
||||
THEN: A ParserRegistry instance is returned.
|
||||
"""
|
||||
registry = get_parser_registry()
|
||||
assert isinstance(registry, ParserRegistry)
|
||||
|
||||
def test_get_parser_registry_same_instance_on_repeated_calls(self) -> None:
|
||||
"""
|
||||
GIVEN: A registry instance was created by a prior call.
|
||||
WHEN: get_parser_registry() is called a second time.
|
||||
THEN: The exact same object (identity) is returned.
|
||||
"""
|
||||
first = get_parser_registry()
|
||||
second = get_parser_registry()
|
||||
assert first is second
|
||||
|
||||
def test_reset_parser_registry_gives_fresh_instance(self) -> None:
|
||||
"""
|
||||
GIVEN: A registry instance already exists.
|
||||
WHEN: reset_parser_registry() is called and then get_parser_registry()
|
||||
is called again.
|
||||
THEN: A new, distinct registry instance is returned.
|
||||
"""
|
||||
first = get_parser_registry()
|
||||
reset_parser_registry()
|
||||
second = get_parser_registry()
|
||||
assert first is not second
|
||||
|
||||
def test_init_builtin_parsers_does_not_run_discover(
|
||||
self,
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: discover() would raise an exception if called.
|
||||
WHEN: init_builtin_parsers() is called.
|
||||
THEN: No exception is raised, confirming discover() was not invoked.
|
||||
"""
|
||||
|
||||
def exploding_discover(self) -> None:
|
||||
raise RuntimeError(
|
||||
"discover() must not be called from init_builtin_parsers",
|
||||
)
|
||||
|
||||
monkeypatch.setattr(ParserRegistry, "discover", exploding_discover)
|
||||
|
||||
# Should complete without raising.
|
||||
init_builtin_parsers()
|
||||
|
||||
def test_init_builtin_parsers_idempotent(self) -> None:
|
||||
"""
|
||||
GIVEN: init_builtin_parsers() has already been called once.
|
||||
WHEN: init_builtin_parsers() is called a second time.
|
||||
THEN: No error is raised and the same registry instance is reused.
|
||||
"""
|
||||
init_builtin_parsers()
|
||||
# Capture the registry created by the first call.
|
||||
import paperless.parsers.registry as reg_module
|
||||
|
||||
first_registry = reg_module._registry
|
||||
|
||||
init_builtin_parsers()
|
||||
|
||||
assert reg_module._registry is first_registry
|
||||
|
||||
|
||||
class TestParserRegistryGetParserForFile:
|
||||
"""Verify parser selection logic in get_parser_for_file()."""
|
||||
|
||||
def test_returns_none_when_no_parsers_registered(self) -> None:
|
||||
"""
|
||||
GIVEN: A registry with no parsers registered.
|
||||
WHEN: get_parser_for_file() is called for any MIME type.
|
||||
THEN: None is returned.
|
||||
"""
|
||||
registry = ParserRegistry()
|
||||
result = registry.get_parser_for_file("text/plain", "doc.txt")
|
||||
assert result is None
|
||||
|
||||
def test_returns_none_for_unsupported_mime_type(
|
||||
self,
|
||||
dummy_parser_cls: type,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A registry with a parser that supports only 'text/plain'.
|
||||
WHEN: get_parser_for_file() is called with 'application/pdf'.
|
||||
THEN: None is returned.
|
||||
"""
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(dummy_parser_cls)
|
||||
result = registry.get_parser_for_file("application/pdf", "file.pdf")
|
||||
assert result is None
|
||||
|
||||
def test_returns_parser_for_supported_mime_type(
|
||||
self,
|
||||
dummy_parser_cls: type,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A registry with a parser registered for 'text/plain'.
|
||||
WHEN: get_parser_for_file() is called with 'text/plain'.
|
||||
THEN: The registered parser class is returned.
|
||||
"""
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(dummy_parser_cls)
|
||||
result = registry.get_parser_for_file("text/plain", "readme.txt")
|
||||
assert result is dummy_parser_cls
|
||||
|
||||
def test_highest_score_wins(self) -> None:
|
||||
"""
|
||||
GIVEN: Two parsers both supporting 'text/plain' with scores 5 and 20.
|
||||
WHEN: get_parser_for_file() is called for 'text/plain'.
|
||||
THEN: The parser with score 20 is returned.
|
||||
"""
|
||||
|
||||
class LowScoreParser:
|
||||
name = "low"
|
||||
version = "1.0"
|
||||
author = "A"
|
||||
url = "https://example.com/low"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 5
|
||||
|
||||
class HighScoreParser:
|
||||
name = "high"
|
||||
version = "1.0"
|
||||
author = "B"
|
||||
url = "https://example.com/high"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 20
|
||||
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(LowScoreParser)
|
||||
registry.register_builtin(HighScoreParser)
|
||||
result = registry.get_parser_for_file("text/plain", "readme.txt")
|
||||
assert result is HighScoreParser
|
||||
|
||||
def test_parser_returning_none_score_is_skipped(self) -> None:
|
||||
"""
|
||||
GIVEN: A parser that returns None from score() for the given file.
|
||||
WHEN: get_parser_for_file() is called.
|
||||
THEN: That parser is skipped and None is returned (no other candidates).
|
||||
"""
|
||||
|
||||
class DecliningParser:
|
||||
name = "declining"
|
||||
version = "1.0"
|
||||
author = "A"
|
||||
url = "https://example.com"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return None # Explicitly declines
|
||||
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(DecliningParser)
|
||||
result = registry.get_parser_for_file("text/plain", "readme.txt")
|
||||
assert result is None
|
||||
|
||||
def test_all_parsers_decline_returns_none(self) -> None:
|
||||
"""
|
||||
GIVEN: Multiple parsers that all return None from score().
|
||||
WHEN: get_parser_for_file() is called.
|
||||
THEN: None is returned.
|
||||
"""
|
||||
|
||||
class AlwaysDeclines:
|
||||
name = "declines"
|
||||
version = "1.0"
|
||||
author = "A"
|
||||
url = "https://example.com"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return None
|
||||
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(AlwaysDeclines)
|
||||
registry._external.append(AlwaysDeclines)
|
||||
result = registry.get_parser_for_file("text/plain", "file.txt")
|
||||
assert result is None
|
||||
|
||||
def test_external_parser_beats_builtin_same_score(self) -> None:
|
||||
"""
|
||||
GIVEN: An external and a built-in parser both returning score 10.
|
||||
WHEN: get_parser_for_file() is called.
|
||||
THEN: The external parser wins because externals are evaluated first
|
||||
and the first-seen-wins policy applies at equal scores.
|
||||
"""
|
||||
|
||||
class BuiltinParser:
|
||||
name = "builtin"
|
||||
version = "1.0"
|
||||
author = "Core"
|
||||
url = "https://example.com/builtin"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 10
|
||||
|
||||
class ExternalParser:
|
||||
name = "external"
|
||||
version = "2.0"
|
||||
author = "Third Party"
|
||||
url = "https://example.com/external"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 10
|
||||
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(BuiltinParser)
|
||||
registry._external.append(ExternalParser)
|
||||
result = registry.get_parser_for_file("text/plain", "file.txt")
|
||||
assert result is ExternalParser
|
||||
|
||||
def test_builtin_wins_when_external_declines(self) -> None:
|
||||
"""
|
||||
GIVEN: An external parser that declines (score None) and a built-in
|
||||
that returns score 5.
|
||||
WHEN: get_parser_for_file() is called.
|
||||
THEN: The built-in parser is returned.
|
||||
"""
|
||||
|
||||
class DecliningExternal:
|
||||
name = "declining-external"
|
||||
version = "1.0"
|
||||
author = "Third Party"
|
||||
url = "https://example.com/declining"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return None
|
||||
|
||||
class AcceptingBuiltin:
|
||||
name = "accepting-builtin"
|
||||
version = "1.0"
|
||||
author = "Core"
|
||||
url = "https://example.com/accepting"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 5
|
||||
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(AcceptingBuiltin)
|
||||
registry._external.append(DecliningExternal)
|
||||
result = registry.get_parser_for_file("text/plain", "file.txt")
|
||||
assert result is AcceptingBuiltin
|
||||
|
||||
|
||||
class TestDiscover:
|
||||
"""Verify entrypoint discovery in ParserRegistry.discover()."""
|
||||
|
||||
def test_discover_with_no_entrypoints(self) -> None:
|
||||
"""
|
||||
GIVEN: No entrypoints are registered under 'paperless_ngx.parsers'.
|
||||
WHEN: discover() is called.
|
||||
THEN: _external remains empty and no errors are raised.
|
||||
"""
|
||||
registry = ParserRegistry()
|
||||
|
||||
with patch(
|
||||
"paperless.parsers.registry.entry_points",
|
||||
return_value=[],
|
||||
):
|
||||
registry.discover()
|
||||
|
||||
assert registry._external == []
|
||||
|
||||
def test_discover_adds_valid_external_parser(self) -> None:
|
||||
"""
|
||||
GIVEN: One valid entrypoint whose loaded class has all required attrs.
|
||||
WHEN: discover() is called.
|
||||
THEN: The class is appended to _external.
|
||||
"""
|
||||
|
||||
class ValidExternal:
|
||||
name = "valid-external"
|
||||
version = "3.0.0"
|
||||
author = "Someone"
|
||||
url = "https://example.com/valid"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"application/pdf": ".pdf"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 5
|
||||
|
||||
mock_ep = MagicMock(spec=EntryPoint)
|
||||
mock_ep.name = "valid_external"
|
||||
mock_ep.load.return_value = ValidExternal
|
||||
|
||||
registry = ParserRegistry()
|
||||
|
||||
with patch(
|
||||
"paperless.parsers.registry.entry_points",
|
||||
return_value=[mock_ep],
|
||||
):
|
||||
registry.discover()
|
||||
|
||||
assert ValidExternal in registry._external
|
||||
|
||||
def test_discover_skips_entrypoint_with_load_error(
|
||||
self,
|
||||
caplog: pytest.LogCaptureFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: An entrypoint whose load() method raises ImportError.
|
||||
WHEN: discover() is called.
|
||||
THEN: The entrypoint is skipped, an error is logged, and _external
|
||||
remains empty.
|
||||
"""
|
||||
mock_ep = MagicMock(spec=EntryPoint)
|
||||
mock_ep.name = "broken_ep"
|
||||
mock_ep.load.side_effect = ImportError("missing dependency")
|
||||
|
||||
registry = ParserRegistry()
|
||||
|
||||
with caplog.at_level(logging.ERROR, logger="paperless.parsers.registry"):
|
||||
with patch(
|
||||
"paperless.parsers.registry.entry_points",
|
||||
return_value=[mock_ep],
|
||||
):
|
||||
registry.discover()
|
||||
|
||||
assert registry._external == []
|
||||
assert any(
|
||||
"broken_ep" in record.message
|
||||
for record in caplog.records
|
||||
if record.levelno >= logging.ERROR
|
||||
)
|
||||
|
||||
def test_discover_skips_entrypoint_with_missing_attrs(
|
||||
self,
|
||||
caplog: pytest.LogCaptureFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A class loaded from an entrypoint that is missing the 'score'
|
||||
attribute.
|
||||
WHEN: discover() is called.
|
||||
THEN: The entrypoint is skipped, a warning is logged, and _external
|
||||
remains empty.
|
||||
"""
|
||||
|
||||
class MissingScore:
|
||||
name = "missing-score"
|
||||
version = "1.0"
|
||||
author = "Someone"
|
||||
url = "https://example.com"
|
||||
|
||||
# 'score' classmethod is intentionally absent.
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
mock_ep = MagicMock(spec=EntryPoint)
|
||||
mock_ep.name = "missing_score_ep"
|
||||
mock_ep.load.return_value = MissingScore
|
||||
|
||||
registry = ParserRegistry()
|
||||
|
||||
with caplog.at_level(logging.WARNING, logger="paperless.parsers.registry"):
|
||||
with patch(
|
||||
"paperless.parsers.registry.entry_points",
|
||||
return_value=[mock_ep],
|
||||
):
|
||||
registry.discover()
|
||||
|
||||
assert registry._external == []
|
||||
assert any(
|
||||
"missing_score_ep" in record.message
|
||||
for record in caplog.records
|
||||
if record.levelno >= logging.WARNING
|
||||
)
|
||||
|
||||
def test_discover_logs_loaded_parser_info(
|
||||
self,
|
||||
caplog: pytest.LogCaptureFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A valid entrypoint that loads successfully.
|
||||
WHEN: discover() is called.
|
||||
THEN: An INFO log message is emitted containing the parser name,
|
||||
version, author, and entrypoint name.
|
||||
"""
|
||||
|
||||
class LoggableParser:
|
||||
name = "loggable"
|
||||
version = "4.2.0"
|
||||
author = "Log Tester"
|
||||
url = "https://example.com/loggable"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"image/png": ".png"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 1
|
||||
|
||||
mock_ep = MagicMock(spec=EntryPoint)
|
||||
mock_ep.name = "loggable_ep"
|
||||
mock_ep.load.return_value = LoggableParser
|
||||
|
||||
registry = ParserRegistry()
|
||||
|
||||
with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
|
||||
with patch(
|
||||
"paperless.parsers.registry.entry_points",
|
||||
return_value=[mock_ep],
|
||||
):
|
||||
registry.discover()
|
||||
|
||||
info_messages = " ".join(
|
||||
r.message for r in caplog.records if r.levelno == logging.INFO
|
||||
)
|
||||
assert "loggable" in info_messages
|
||||
assert "4.2.0" in info_messages
|
||||
assert "Log Tester" in info_messages
|
||||
assert "loggable_ep" in info_messages
|
||||
|
||||
|
||||
class TestLogSummary:
|
||||
"""Verify log output from ParserRegistry.log_summary()."""
|
||||
|
||||
def test_log_summary_with_no_external_parsers(
|
||||
self,
|
||||
dummy_parser_cls: type,
|
||||
caplog: pytest.LogCaptureFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A registry with one built-in parser and no external parsers.
|
||||
WHEN: log_summary() is called.
|
||||
THEN: The built-in parser name appears in the logs.
|
||||
"""
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(dummy_parser_cls)
|
||||
|
||||
with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
|
||||
registry.log_summary()
|
||||
|
||||
all_messages = " ".join(r.message for r in caplog.records)
|
||||
assert dummy_parser_cls.name in all_messages
|
||||
|
||||
def test_log_summary_with_external_parsers(
|
||||
self,
|
||||
caplog: pytest.LogCaptureFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A registry with one external parser registered.
|
||||
WHEN: log_summary() is called.
|
||||
THEN: The external parser name, version, author, and url appear in
|
||||
the log output.
|
||||
"""
|
||||
|
||||
class ExtParser:
|
||||
name = "ext-parser"
|
||||
version = "9.9.9"
|
||||
author = "Ext Corp"
|
||||
url = "https://ext.example.com"
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return None
|
||||
|
||||
registry = ParserRegistry()
|
||||
registry._external.append(ExtParser)
|
||||
|
||||
with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
|
||||
registry.log_summary()
|
||||
|
||||
all_messages = " ".join(r.message for r in caplog.records)
|
||||
assert "ext-parser" in all_messages
|
||||
assert "9.9.9" in all_messages
|
||||
assert "Ext Corp" in all_messages
|
||||
assert "https://ext.example.com" in all_messages
|
||||
|
||||
def test_log_summary_logs_no_third_party_message_when_none(
|
||||
self,
|
||||
caplog: pytest.LogCaptureFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A registry with no external parsers.
|
||||
WHEN: log_summary() is called.
|
||||
THEN: A message containing 'No third-party parsers discovered.' is
|
||||
logged.
|
||||
"""
|
||||
registry = ParserRegistry()
|
||||
|
||||
with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
|
||||
registry.log_summary()
|
||||
|
||||
all_messages = " ".join(r.message for r in caplog.records)
|
||||
assert "No third-party parsers discovered." in all_messages
|
||||
@@ -1,174 +1,186 @@
|
||||
import pytest
|
||||
from unittest import mock
|
||||
|
||||
from channels.layers import get_channel_layer
|
||||
from channels.testing import WebsocketCommunicator
|
||||
from pytest_mock import MockerFixture
|
||||
from django.test import TestCase
|
||||
from django.test import override_settings
|
||||
|
||||
from documents.plugins.helpers import DocumentsStatusManager
|
||||
from documents.plugins.helpers import ProgressManager
|
||||
from documents.plugins.helpers import ProgressStatusOptions
|
||||
from paperless.asgi import application
|
||||
|
||||
TEST_CHANNEL_LAYERS = {
|
||||
"default": {
|
||||
"BACKEND": "channels.layers.InMemoryChannelLayer",
|
||||
},
|
||||
}
|
||||
|
||||
class TestWebSockets:
|
||||
@pytest.fixture(autouse=True)
|
||||
def anyio_backend(self) -> str:
|
||||
return "asyncio"
|
||||
|
||||
@pytest.mark.anyio
|
||||
@override_settings(CHANNEL_LAYERS=TEST_CHANNEL_LAYERS)
|
||||
class TestWebSockets(TestCase):
|
||||
async def test_no_auth(self) -> None:
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
connected, _ = await communicator.connect()
|
||||
assert not connected
|
||||
self.assertFalse(connected)
|
||||
await communicator.disconnect()
|
||||
|
||||
@pytest.mark.anyio
|
||||
async def test_close_on_no_auth(self, mocker: MockerFixture) -> None:
|
||||
mock_auth = mocker.patch(
|
||||
"paperless.consumers.StatusConsumer._authenticated",
|
||||
return_value=True,
|
||||
)
|
||||
mock_close = mocker.patch(
|
||||
"paperless.consumers.StatusConsumer.close",
|
||||
new_callable=mocker.AsyncMock,
|
||||
)
|
||||
@mock.patch("paperless.consumers.StatusConsumer.close")
|
||||
@mock.patch("paperless.consumers.StatusConsumer._authenticated")
|
||||
async def test_close_on_no_auth(self, _authenticated, mock_close) -> None:
|
||||
_authenticated.return_value = True
|
||||
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
connected, _ = await communicator.connect()
|
||||
assert connected
|
||||
|
||||
mock_auth.return_value = False
|
||||
channel_layer = get_channel_layer()
|
||||
assert channel_layer is not None
|
||||
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
{"type": "status_update", "data": {"task_id": "test"}},
|
||||
)
|
||||
await communicator.receive_nothing()
|
||||
mock_close.assert_awaited_once()
|
||||
mock_close.reset_mock()
|
||||
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
{
|
||||
"type": "document_updated",
|
||||
"data": {"document_id": 10, "modified": "2026-02-17T00:00:00Z"},
|
||||
},
|
||||
)
|
||||
await communicator.receive_nothing()
|
||||
mock_close.assert_awaited_once()
|
||||
mock_close.reset_mock()
|
||||
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
{"type": "documents_deleted", "data": {"documents": [1, 2, 3]}},
|
||||
)
|
||||
await communicator.receive_nothing()
|
||||
mock_close.assert_awaited_once()
|
||||
|
||||
@pytest.mark.anyio
|
||||
async def test_auth(self, mocker: MockerFixture) -> None:
|
||||
mocker.patch(
|
||||
"paperless.consumers.StatusConsumer._authenticated",
|
||||
return_value=True,
|
||||
)
|
||||
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
connected, _ = await communicator.connect()
|
||||
assert connected
|
||||
|
||||
await communicator.disconnect()
|
||||
|
||||
@pytest.mark.anyio
|
||||
async def test_receive_status_update(self, mocker: MockerFixture) -> None:
|
||||
mocker.patch(
|
||||
"paperless.consumers.StatusConsumer._authenticated",
|
||||
return_value=True,
|
||||
)
|
||||
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
connected, _ = await communicator.connect()
|
||||
assert connected
|
||||
self.assertTrue(connected)
|
||||
|
||||
message = {"type": "status_update", "data": {"task_id": "test"}}
|
||||
channel_layer = get_channel_layer()
|
||||
assert channel_layer is not None
|
||||
await channel_layer.group_send("status_updates", message)
|
||||
|
||||
assert await communicator.receive_json_from() == message
|
||||
_authenticated.return_value = False
|
||||
|
||||
channel_layer = get_channel_layer()
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
await communicator.receive_nothing()
|
||||
|
||||
mock_close.assert_called_once()
|
||||
mock_close.reset_mock()
|
||||
|
||||
message = {
|
||||
"type": "document_updated",
|
||||
"data": {"document_id": 10, "modified": "2026-02-17T00:00:00Z"},
|
||||
}
|
||||
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
await communicator.receive_nothing()
|
||||
|
||||
mock_close.assert_called_once()
|
||||
mock_close.reset_mock()
|
||||
|
||||
message = {"type": "documents_deleted", "data": {"documents": [1, 2, 3]}}
|
||||
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
await communicator.receive_nothing()
|
||||
|
||||
mock_close.assert_called_once()
|
||||
|
||||
@mock.patch("paperless.consumers.StatusConsumer._authenticated")
|
||||
async def test_auth(self, _authenticated) -> None:
|
||||
_authenticated.return_value = True
|
||||
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
connected, _ = await communicator.connect()
|
||||
self.assertTrue(connected)
|
||||
|
||||
await communicator.disconnect()
|
||||
|
||||
@pytest.mark.anyio
|
||||
async def test_status_update_check_perms(self, mocker: MockerFixture) -> None:
|
||||
user = mocker.MagicMock()
|
||||
user.is_authenticated = True
|
||||
user.is_superuser = False
|
||||
user.id = 1
|
||||
@mock.patch("paperless.consumers.StatusConsumer._authenticated")
|
||||
async def test_receive_status_update(self, _authenticated) -> None:
|
||||
_authenticated.return_value = True
|
||||
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
communicator.scope["user"] = user # type: ignore[typeddict-unknown-key]
|
||||
connected, _ = await communicator.connect()
|
||||
assert connected
|
||||
self.assertTrue(connected)
|
||||
|
||||
message = {"type": "status_update", "data": {"task_id": "test"}}
|
||||
|
||||
channel_layer = get_channel_layer()
|
||||
assert channel_layer is not None
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
|
||||
# Message received as owner
|
||||
response = await communicator.receive_json_from()
|
||||
|
||||
self.assertEqual(response, message)
|
||||
|
||||
await communicator.disconnect()
|
||||
|
||||
async def test_status_update_check_perms(self) -> None:
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
|
||||
communicator.scope["user"] = mock.Mock()
|
||||
communicator.scope["user"].is_authenticated = True
|
||||
communicator.scope["user"].is_superuser = False
|
||||
communicator.scope["user"].id = 1
|
||||
|
||||
connected, _ = await communicator.connect()
|
||||
self.assertTrue(connected)
|
||||
|
||||
# Test as owner
|
||||
message = {"type": "status_update", "data": {"task_id": "test", "owner_id": 1}}
|
||||
await channel_layer.group_send("status_updates", message)
|
||||
assert await communicator.receive_json_from() == message
|
||||
channel_layer = get_channel_layer()
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
response = await communicator.receive_json_from()
|
||||
self.assertEqual(response, message)
|
||||
|
||||
# Message received via group membership
|
||||
user.groups.filter.return_value.aexists = mocker.AsyncMock(return_value=True)
|
||||
# Test with a group that the user belongs to
|
||||
communicator.scope["user"].groups.filter.return_value.exists.return_value = True
|
||||
message = {
|
||||
"type": "status_update",
|
||||
"data": {"task_id": "test", "owner_id": 2, "groups_can_view": [1]},
|
||||
}
|
||||
await channel_layer.group_send("status_updates", message)
|
||||
assert await communicator.receive_json_from() == message
|
||||
channel_layer = get_channel_layer()
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
response = await communicator.receive_json_from()
|
||||
self.assertEqual(response, message)
|
||||
|
||||
# Message not received for different owner with no group match
|
||||
# Test with a different owner_id
|
||||
message = {"type": "status_update", "data": {"task_id": "test", "owner_id": 2}}
|
||||
await channel_layer.group_send("status_updates", message)
|
||||
assert await communicator.receive_nothing()
|
||||
|
||||
channel_layer = get_channel_layer()
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
response = await communicator.receive_nothing()
|
||||
self.assertNotEqual(response, message)
|
||||
await communicator.disconnect()
|
||||
|
||||
@pytest.mark.anyio
|
||||
async def test_receive_documents_deleted(self, mocker: MockerFixture) -> None:
|
||||
mocker.patch(
|
||||
"paperless.consumers.StatusConsumer._authenticated",
|
||||
return_value=True,
|
||||
)
|
||||
@mock.patch("paperless.consumers.StatusConsumer._authenticated")
|
||||
async def test_receive_documents_deleted(self, _authenticated) -> None:
|
||||
_authenticated.return_value = True
|
||||
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
connected, _ = await communicator.connect()
|
||||
assert connected
|
||||
self.assertTrue(connected)
|
||||
|
||||
message = {"type": "documents_deleted", "data": {"documents": [1, 2, 3]}}
|
||||
channel_layer = get_channel_layer()
|
||||
assert channel_layer is not None
|
||||
await channel_layer.group_send("status_updates", message)
|
||||
|
||||
assert await communicator.receive_json_from() == message
|
||||
channel_layer = get_channel_layer()
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
|
||||
response = await communicator.receive_json_from()
|
||||
|
||||
self.assertEqual(response, message)
|
||||
|
||||
await communicator.disconnect()
|
||||
|
||||
@pytest.mark.anyio
|
||||
async def test_receive_document_updated(self, mocker: MockerFixture) -> None:
|
||||
mocker.patch(
|
||||
"paperless.consumers.StatusConsumer._authenticated",
|
||||
return_value=True,
|
||||
)
|
||||
mocker.patch(
|
||||
"paperless.consumers.StatusConsumer._can_view",
|
||||
return_value=True,
|
||||
)
|
||||
@mock.patch("paperless.consumers.StatusConsumer._can_view")
|
||||
@mock.patch("paperless.consumers.StatusConsumer._authenticated")
|
||||
async def test_receive_document_updated(self, _authenticated, _can_view) -> None:
|
||||
_authenticated.return_value = True
|
||||
_can_view.return_value = True
|
||||
|
||||
communicator = WebsocketCommunicator(application, "/ws/status/")
|
||||
connected, _ = await communicator.connect()
|
||||
assert connected
|
||||
self.assertTrue(connected)
|
||||
|
||||
message = {
|
||||
"type": "document_updated",
|
||||
@@ -180,58 +192,67 @@ class TestWebSockets:
|
||||
"groups_can_view": [],
|
||||
},
|
||||
}
|
||||
|
||||
channel_layer = get_channel_layer()
|
||||
assert channel_layer is not None
|
||||
await channel_layer.group_send("status_updates", message)
|
||||
await channel_layer.group_send(
|
||||
"status_updates",
|
||||
message,
|
||||
)
|
||||
|
||||
assert await communicator.receive_json_from() == message
|
||||
response = await communicator.receive_json_from()
|
||||
|
||||
self.assertEqual(response, message)
|
||||
|
||||
await communicator.disconnect()
|
||||
|
||||
def test_manager_send_progress(self, mocker: MockerFixture) -> None:
|
||||
mock_group_send = mocker.patch(
|
||||
"channels.layers.InMemoryChannelLayer.group_send",
|
||||
)
|
||||
|
||||
@mock.patch("channels.layers.InMemoryChannelLayer.group_send")
|
||||
def test_manager_send_progress(self, mock_group_send) -> None:
|
||||
with ProgressManager(task_id="test") as manager:
|
||||
manager.send_progress(
|
||||
ProgressStatusOptions.STARTED,
|
||||
"Test message",
|
||||
1,
|
||||
10,
|
||||
document_id=42,
|
||||
owner_id=1,
|
||||
users_can_view=[2, 3],
|
||||
groups_can_view=[4],
|
||||
extra_args={
|
||||
"foo": "bar",
|
||||
},
|
||||
)
|
||||
|
||||
assert mock_group_send.call_args[0][1] == {
|
||||
"type": "status_update",
|
||||
"data": {
|
||||
"filename": None,
|
||||
"task_id": "test",
|
||||
"current_progress": 1,
|
||||
"max_progress": 10,
|
||||
"status": ProgressStatusOptions.STARTED,
|
||||
"message": "Test message",
|
||||
"document_id": 42,
|
||||
"owner_id": 1,
|
||||
"users_can_view": [2, 3],
|
||||
"groups_can_view": [4],
|
||||
},
|
||||
}
|
||||
message = mock_group_send.call_args[0][1]
|
||||
|
||||
def test_manager_send_documents_deleted(self, mocker: MockerFixture) -> None:
|
||||
mock_group_send = mocker.patch(
|
||||
"channels.layers.InMemoryChannelLayer.group_send",
|
||||
self.assertEqual(
|
||||
message,
|
||||
{
|
||||
"type": "status_update",
|
||||
"data": {
|
||||
"filename": None,
|
||||
"task_id": "test",
|
||||
"current_progress": 1,
|
||||
"max_progress": 10,
|
||||
"status": ProgressStatusOptions.STARTED,
|
||||
"message": "Test message",
|
||||
"foo": "bar",
|
||||
},
|
||||
},
|
||||
)
|
||||
|
||||
@mock.patch("channels.layers.InMemoryChannelLayer.group_send")
|
||||
def test_manager_send_documents_deleted(
|
||||
self,
|
||||
mock_group_send: mock.MagicMock,
|
||||
) -> None:
|
||||
with DocumentsStatusManager() as manager:
|
||||
manager.send_documents_deleted([1, 2, 3])
|
||||
|
||||
assert mock_group_send.call_args[0][1] == {
|
||||
"type": "documents_deleted",
|
||||
"data": {
|
||||
"documents": [1, 2, 3],
|
||||
message = mock_group_send.call_args[0][1]
|
||||
|
||||
self.assertEqual(
|
||||
message,
|
||||
{
|
||||
"type": "documents_deleted",
|
||||
"data": {
|
||||
"documents": [1, 2, 3],
|
||||
},
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
@@ -21,18 +21,12 @@ from documents.views import BulkEditView
|
||||
from documents.views import ChatStreamingView
|
||||
from documents.views import CorrespondentViewSet
|
||||
from documents.views import CustomFieldViewSet
|
||||
from documents.views import DeleteDocumentsView
|
||||
from documents.views import DocumentTypeViewSet
|
||||
from documents.views import EditPdfDocumentsView
|
||||
from documents.views import GlobalSearchView
|
||||
from documents.views import IndexView
|
||||
from documents.views import LogViewSet
|
||||
from documents.views import MergeDocumentsView
|
||||
from documents.views import PostDocumentView
|
||||
from documents.views import RemoteVersionView
|
||||
from documents.views import RemovePasswordDocumentsView
|
||||
from documents.views import ReprocessDocumentsView
|
||||
from documents.views import RotateDocumentsView
|
||||
from documents.views import SavedViewViewSet
|
||||
from documents.views import SearchAutoCompleteView
|
||||
from documents.views import SelectionDataView
|
||||
@@ -138,36 +132,6 @@ urlpatterns = [
|
||||
BulkEditView.as_view(),
|
||||
name="bulk_edit",
|
||||
),
|
||||
re_path(
|
||||
"^delete/",
|
||||
DeleteDocumentsView.as_view(),
|
||||
name="delete_documents",
|
||||
),
|
||||
re_path(
|
||||
"^reprocess/",
|
||||
ReprocessDocumentsView.as_view(),
|
||||
name="reprocess_documents",
|
||||
),
|
||||
re_path(
|
||||
"^rotate/",
|
||||
RotateDocumentsView.as_view(),
|
||||
name="rotate_documents",
|
||||
),
|
||||
re_path(
|
||||
"^merge/",
|
||||
MergeDocumentsView.as_view(),
|
||||
name="merge_documents",
|
||||
),
|
||||
re_path(
|
||||
"^edit_pdf/",
|
||||
EditPdfDocumentsView.as_view(),
|
||||
name="edit_pdf_documents",
|
||||
),
|
||||
re_path(
|
||||
"^remove_password/",
|
||||
RemovePasswordDocumentsView.as_view(),
|
||||
name="remove_password_documents",
|
||||
),
|
||||
re_path(
|
||||
"^bulk_download/",
|
||||
BulkDownloadView.as_view(),
|
||||
|
||||
@@ -1,50 +0,0 @@
|
||||
from pathlib import Path
|
||||
|
||||
from django.conf import settings
|
||||
from PIL import Image
|
||||
from PIL import ImageDraw
|
||||
from PIL import ImageFont
|
||||
|
||||
from documents.parsers import DocumentParser
|
||||
|
||||
|
||||
class TextDocumentParser(DocumentParser):
|
||||
"""
|
||||
This parser directly parses a text document (.txt, .md, or .csv)
|
||||
"""
|
||||
|
||||
logging_name = "paperless.parsing.text"
|
||||
|
||||
def get_thumbnail(self, document_path: Path, mime_type, file_name=None) -> Path:
|
||||
# Avoid reading entire file into memory
|
||||
max_chars = 100_000
|
||||
file_size_limit = 50 * 1024 * 1024
|
||||
|
||||
if document_path.stat().st_size > file_size_limit:
|
||||
text = "[File too large to preview]"
|
||||
else:
|
||||
with Path(document_path).open("r", encoding="utf-8", errors="replace") as f:
|
||||
text = f.read(max_chars)
|
||||
|
||||
img = Image.new("RGB", (500, 700), color="white")
|
||||
draw = ImageDraw.Draw(img)
|
||||
font = ImageFont.truetype(
|
||||
font=settings.THUMBNAIL_FONT_NAME,
|
||||
size=20,
|
||||
layout_engine=ImageFont.Layout.BASIC,
|
||||
)
|
||||
draw.multiline_text((5, 5), text, font=font, fill="black", spacing=4)
|
||||
|
||||
out_path = self.tempdir / "thumb.webp"
|
||||
img.save(out_path, format="WEBP")
|
||||
|
||||
return out_path
|
||||
|
||||
def parse(self, document_path, mime_type, file_name=None) -> None:
|
||||
self.text = self.read_file_handle_unicode_errors(document_path)
|
||||
|
||||
def get_settings(self) -> None:
|
||||
"""
|
||||
This parser does not implement additional settings yet
|
||||
"""
|
||||
return None
|
||||
@@ -1,7 +1,13 @@
|
||||
def get_parser(*args, **kwargs):
|
||||
from paperless_text.parsers import TextDocumentParser
|
||||
from paperless.parsers.text import TextDocumentParser
|
||||
|
||||
return TextDocumentParser(*args, **kwargs)
|
||||
# The new TextDocumentParser does not accept the legacy logging_group /
|
||||
# progress_callback kwargs injected by the old signal-based consumer.
|
||||
# These are dropped here; Phase 4 will replace this signal path with the
|
||||
# new ParserRegistry so the shim can be removed at that point.
|
||||
kwargs.pop("logging_group", None)
|
||||
kwargs.pop("progress_callback", None)
|
||||
return TextDocumentParser()
|
||||
|
||||
|
||||
def text_consumer_declaration(sender, **kwargs):
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
from collections.abc import Generator
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from paperless_text.parsers import TextDocumentParser
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_dir() -> Path:
|
||||
return (Path(__file__).parent / Path("samples")).resolve()
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def text_parser() -> Generator[TextDocumentParser, None, None]:
|
||||
try:
|
||||
parser = TextDocumentParser(logging_group=None)
|
||||
yield parser
|
||||
finally:
|
||||
parser.cleanup()
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_txt_file(sample_dir: Path) -> Path:
|
||||
return sample_dir / "test.txt"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def malformed_txt_file(sample_dir: Path) -> Path:
|
||||
return sample_dir / "decode_error.txt"
|
||||
@@ -1,69 +0,0 @@
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
from paperless_text.parsers import TextDocumentParser
|
||||
|
||||
|
||||
class TestTextParser:
|
||||
def test_thumbnail(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
# just make sure that it does not crash
|
||||
f = text_parser.get_thumbnail(sample_txt_file, "text/plain")
|
||||
assert f.exists()
|
||||
assert f.is_file()
|
||||
|
||||
def test_parse(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
sample_txt_file: Path,
|
||||
) -> None:
|
||||
text_parser.parse(sample_txt_file, "text/plain")
|
||||
|
||||
assert text_parser.get_text() == "This is a test file.\n"
|
||||
assert text_parser.get_archive_path() is None
|
||||
|
||||
def test_parse_invalid_bytes(
|
||||
self,
|
||||
text_parser: TextDocumentParser,
|
||||
malformed_txt_file: Path,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Text file which contains invalid UTF bytes
|
||||
WHEN:
|
||||
- The file is parsed
|
||||
THEN:
|
||||
- Parsing continues
|
||||
- Invalid bytes are removed
|
||||
"""
|
||||
|
||||
text_parser.parse(malformed_txt_file, "text/plain")
|
||||
|
||||
assert text_parser.get_text() == "Pantothens<EFBFBD>ure\n"
|
||||
assert text_parser.get_archive_path() is None
|
||||
|
||||
def test_thumbnail_large_file(self, text_parser: TextDocumentParser) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A very large text file (>50MB)
|
||||
WHEN:
|
||||
- A thumbnail is requested
|
||||
THEN:
|
||||
- A thumbnail is created without reading the entire file into memory
|
||||
"""
|
||||
with tempfile.NamedTemporaryFile(
|
||||
delete=False,
|
||||
mode="w",
|
||||
encoding="utf-8",
|
||||
suffix=".txt",
|
||||
) as tmp:
|
||||
tmp.write("A" * (51 * 1024 * 1024)) # 51 MB of 'A'
|
||||
large_file = Path(tmp.name)
|
||||
|
||||
thumb = text_parser.get_thumbnail(large_file, "text/plain")
|
||||
assert thumb.exists()
|
||||
assert thumb.is_file()
|
||||
large_file.unlink()
|
||||
@@ -1,136 +0,0 @@
|
||||
from pathlib import Path
|
||||
|
||||
import httpx
|
||||
from django.conf import settings
|
||||
from django.utils import timezone
|
||||
from gotenberg_client import GotenbergClient
|
||||
from gotenberg_client.options import PdfAFormat
|
||||
from tika_client import TikaClient
|
||||
|
||||
from documents.parsers import DocumentParser
|
||||
from documents.parsers import ParseError
|
||||
from documents.parsers import make_thumbnail_from_pdf
|
||||
from paperless.config import OutputTypeConfig
|
||||
from paperless.models import OutputTypeChoices
|
||||
|
||||
|
||||
class TikaDocumentParser(DocumentParser):
|
||||
"""
|
||||
This parser sends documents to a local tika server
|
||||
"""
|
||||
|
||||
logging_name = "paperless.parsing.tika"
|
||||
|
||||
def get_thumbnail(self, document_path, mime_type, file_name=None):
|
||||
if not self.archive_path:
|
||||
self.archive_path = self.convert_to_pdf(document_path, file_name)
|
||||
|
||||
return make_thumbnail_from_pdf(
|
||||
self.archive_path,
|
||||
self.tempdir,
|
||||
self.logging_group,
|
||||
)
|
||||
|
||||
def extract_metadata(self, document_path, mime_type):
|
||||
try:
|
||||
with TikaClient(
|
||||
tika_url=settings.TIKA_ENDPOINT,
|
||||
timeout=settings.CELERY_TASK_TIME_LIMIT,
|
||||
) as client:
|
||||
parsed = client.metadata.from_file(document_path, mime_type)
|
||||
return [
|
||||
{
|
||||
"namespace": "",
|
||||
"prefix": "",
|
||||
"key": key,
|
||||
"value": parsed.data[key],
|
||||
}
|
||||
for key in parsed.data
|
||||
]
|
||||
except Exception as e:
|
||||
self.log.warning(
|
||||
f"Error while fetching document metadata for {document_path}: {e}",
|
||||
)
|
||||
return []
|
||||
|
||||
def parse(self, document_path: Path, mime_type: str, file_name=None) -> None:
|
||||
self.log.info(f"Sending {document_path} to Tika server")
|
||||
|
||||
try:
|
||||
with TikaClient(
|
||||
tika_url=settings.TIKA_ENDPOINT,
|
||||
timeout=settings.CELERY_TASK_TIME_LIMIT,
|
||||
) as client:
|
||||
try:
|
||||
parsed = client.tika.as_text.from_file(document_path, mime_type)
|
||||
except httpx.HTTPStatusError as err:
|
||||
# Workaround https://issues.apache.org/jira/browse/TIKA-4110
|
||||
# Tika fails with some files as multi-part form data
|
||||
if err.response.status_code == httpx.codes.INTERNAL_SERVER_ERROR:
|
||||
parsed = client.tika.as_text.from_buffer(
|
||||
document_path.read_bytes(),
|
||||
mime_type,
|
||||
)
|
||||
else: # pragma: no cover
|
||||
raise
|
||||
except Exception as err:
|
||||
raise ParseError(
|
||||
f"Could not parse {document_path} with tika server at "
|
||||
f"{settings.TIKA_ENDPOINT}: {err}",
|
||||
) from err
|
||||
|
||||
self.text = parsed.content
|
||||
if self.text is not None:
|
||||
self.text = self.text.strip()
|
||||
|
||||
self.date = parsed.created
|
||||
if self.date is not None and timezone.is_naive(self.date):
|
||||
self.date = timezone.make_aware(self.date)
|
||||
|
||||
self.archive_path = self.convert_to_pdf(document_path, file_name)
|
||||
|
||||
def convert_to_pdf(self, document_path: Path, file_name):
|
||||
pdf_path = Path(self.tempdir) / "convert.pdf"
|
||||
|
||||
self.log.info(f"Converting {document_path} to PDF as {pdf_path}")
|
||||
|
||||
with (
|
||||
GotenbergClient(
|
||||
host=settings.TIKA_GOTENBERG_ENDPOINT,
|
||||
timeout=settings.CELERY_TASK_TIME_LIMIT,
|
||||
) as client,
|
||||
client.libre_office.to_pdf() as route,
|
||||
):
|
||||
# Set the output format of the resulting PDF
|
||||
if settings.OCR_OUTPUT_TYPE in {
|
||||
OutputTypeChoices.PDF_A,
|
||||
OutputTypeChoices.PDF_A2,
|
||||
}:
|
||||
route.pdf_format(PdfAFormat.A2b)
|
||||
elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A1:
|
||||
self.log.warning(
|
||||
"Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
|
||||
)
|
||||
route.pdf_format(PdfAFormat.A2b)
|
||||
elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A3:
|
||||
route.pdf_format(PdfAFormat.A3b)
|
||||
|
||||
route.convert(document_path)
|
||||
|
||||
try:
|
||||
response = route.run()
|
||||
|
||||
pdf_path.write_bytes(response.content)
|
||||
|
||||
return pdf_path
|
||||
|
||||
except Exception as err:
|
||||
raise ParseError(
|
||||
f"Error while converting document to PDF: {err}",
|
||||
) from err
|
||||
|
||||
def get_settings(self) -> OutputTypeConfig:
|
||||
"""
|
||||
This parser only uses the PDF output type configuration currently
|
||||
"""
|
||||
return OutputTypeConfig()
|
||||
@@ -1,7 +1,13 @@
|
||||
def get_parser(*args, **kwargs):
|
||||
from paperless_tika.parsers import TikaDocumentParser
|
||||
from paperless.parsers.tika import TikaDocumentParser
|
||||
|
||||
return TikaDocumentParser(*args, **kwargs)
|
||||
# The new TikaDocumentParser does not accept the legacy logging_group /
|
||||
# progress_callback kwargs injected by the old signal-based consumer.
|
||||
# These are dropped here; Phase 4 will replace this signal path with the
|
||||
# new ParserRegistry so the shim can be removed at that point.
|
||||
kwargs.pop("logging_group", None)
|
||||
kwargs.pop("progress_callback", None)
|
||||
return TikaDocumentParser()
|
||||
|
||||
|
||||
def tika_consumer_declaration(sender, **kwargs):
|
||||
|
||||
@@ -1,40 +0,0 @@
|
||||
from collections.abc import Generator
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from paperless_tika.parsers import TikaDocumentParser
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def tika_parser() -> Generator[TikaDocumentParser, None, None]:
|
||||
try:
|
||||
parser = TikaDocumentParser(logging_group=None)
|
||||
yield parser
|
||||
finally:
|
||||
parser.cleanup()
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_dir() -> Path:
|
||||
return (Path(__file__).parent / Path("samples")).resolve()
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_odt_file(sample_dir: Path) -> Path:
|
||||
return sample_dir / "sample.odt"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_docx_file(sample_dir: Path) -> Path:
|
||||
return sample_dir / "sample.docx"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_doc_file(sample_dir: Path) -> Path:
|
||||
return sample_dir / "sample.doc"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_broken_odt(sample_dir: Path) -> Path:
|
||||
return sample_dir / "multi-part-broken.odt"
|
||||
126
uv.lock
generated
126
uv.lock
generated
@@ -1393,74 +1393,74 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "granian"
|
||||
version = "2.7.2"
|
||||
version = "2.7.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "click", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/57/19/d4ea523715ba8dd2ed295932cc3dda6bb197060f78aada6e886ff08587b2/granian-2.7.2.tar.gz", hash = "sha256:cdae2f3a26fa998d41fefad58f1d1c84a0b035a6cc9377addd81b51ba82f927f", size = 128969, upload-time = "2026-02-24T23:04:23.314Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/43/75/bdea4ab49a02772a3007e667284764081d401169e96d0270d95509e3e240/granian-2.7.0.tar.gz", hash = "sha256:bee8e8a81a259e6f08613c973062df9db5f8451b521bb0259ed8f27d3e2bab23", size = 127963, upload-time = "2026-02-02T11:39:57.525Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f8/58/dcf0e8a54b9a7f8b7482ed617bca08503a47eb6b702aea73cda9efd2c81c/granian-2.7.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:3a0d33ada95a1421e5a22d447d918e5615ff0aa37f12de5b84455afe89970875", size = 6522860, upload-time = "2026-02-24T23:02:15.901Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2b/dd/398de0f273fdcf0e96bd70d8cd97364625176990e67457f11e23f95772bd/granian-2.7.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ee26f0258cc1b6ccf87c7bdcee6d1f90710505522fc9880ec02b299fb15679ad", size = 6135934, upload-time = "2026-02-24T23:02:18.52Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/67/b7/7bf635bbdfb88dfc6591fa2ce5c3837ab9535e57e197a780c4a338363de7/granian-2.7.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f52338cfab08b8cdaadaa5b93665e0be5b4c4f718fbd132d76ceacacb9ff864e", size = 7138393, upload-time = "2026-02-24T23:02:19.911Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/90/e424fd8a703add1e8922390503be8d057882b35b42ba51796157aabd659b/granian-2.7.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6e377d03a638fecb6949ab05c8fd4a76f892993aed17c602d179bfd56aebc2de", size = 6467189, upload-time = "2026-02-24T23:02:21.896Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/65/9a/5de24d7e2dba1aa9fbac6f0a80dace975cfac1b7c7624ece21da75a38987/granian-2.7.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f742f3ca1797a746fae4a9337fe5d966460c957fa8efeaccf464b872e158d3d", size = 6870813, upload-time = "2026-02-24T23:02:23.972Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ac/cd/a604e38237857f4ad4262eadc409f94fe08fed3e86fa0b8734479cc5bfb1/granian-2.7.2-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:ca4402e8f28a958f0c0f6ebff94cd0b04ca79690aded785648a438bc3c875ba3", size = 7046583, upload-time = "2026-02-24T23:02:25.94Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/cc/ad/79eaae0cddd90c4e191b37674cedd8f4863b44465cb435b10396d0f12c82/granian-2.7.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1f9a899123b0d084783626e5225608094f1d2f6fc81b3a7c77ab8daac33ab74a", size = 7121958, upload-time = "2026-02-24T23:02:27.641Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ca/51/e5c923b1baa003f5b4b7fc148be6f8d2e3cabe55d41040fe8139da52e31b/granian-2.7.2-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:56ba4bef79d0ae3736328038deed2b5d281b11672bc0b08ffc8ce6210e406ef8", size = 7303047, upload-time = "2026-02-24T23:02:30.863Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/06/c0/ebd68144a3ce9ead1a3192ac02e1c26e4874df1257435ce6137adf92fedb/granian-2.7.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:ea46e3f43d94715aa89d1f2f5754753d46e6b653d561b82b0291e62a31bdfb35", size = 7011349, upload-time = "2026-02-24T23:02:32.887Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ec/ed/37f5d7d887ec9159dd8f5b1c9c38cee711d51016d203959f2d51c536a33b/granian-2.7.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:a836f3f8ebfe61cb25d9afb655f2e5d3851154fd2ad97d47bb4fb202817212fc", size = 6451593, upload-time = "2026-02-24T23:02:36.203Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1e/06/84ee67a68504836a52c48ec3b4b2b406cbd927c9b43aae89d82db8d097a0/granian-2.7.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:09b1c543ba30886dea515a156baf6d857bbb8b57dbfd8b012c578b93c80ef0c3", size = 6101239, upload-time = "2026-02-24T23:02:37.636Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ed/50/ece7dc8efe144542cd626b88b1475b649e2eaa3eb5f7541ca57390151b05/granian-2.7.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6d334d4fbefb97001e78aa8067deafb107b867c102ba2120b4b2ec989fa58a89", size = 7079443, upload-time = "2026-02-24T23:02:39.651Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/e8/0f37b531d3cc96b8538cca2dc86eda92102e0ee345b30aa689354194a4cb/granian-2.7.2-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8c86081d8c87989db69650e9d0e50ed925b8cd5dad21e0a86aa72d7a45f45925", size = 6428683, upload-time = "2026-02-24T23:02:41.827Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/47/09/228626706554b389407270e2a6b19b7dee06d6890e8c01a39c6a785827fd/granian-2.7.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d9eda33dca2c8bc6471bb6e9e25863077bca3877a1bba4069cd5e0ee2de41765", size = 6959520, upload-time = "2026-02-24T23:02:43.488Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/61/c0/a639ceabd59b8acae2d71b5c918fcb2d42f8ef98994eedcf9a8b6813731d/granian-2.7.2-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:9cf69aaff6f632074ffbe7c1ee214e50f64be36101b7cb8253eeec1d460f2dba", size = 6991548, upload-time = "2026-02-24T23:02:44.954Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b1/99/a35ed838a3095dcad02ae3944d19ebafe1d5a98cdc72bb61835fb5faf933/granian-2.7.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:f761a748cc7f3843b430422d2539da679daf5d3ef0259a101b90d5e55a0aafa7", size = 7121475, upload-time = "2026-02-24T23:02:46.991Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ce/24/3952c464432b904ec1cf537d2bd80d2dfde85524fa428ab9db2b5afe653c/granian-2.7.2-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:41c7b8390b78647fe34662ed7296e1465dad4a5112af9b0ecf8e367083d6c76a", size = 7243647, upload-time = "2026-02-24T23:02:49.165Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c9/fa/ab39e39c6b78eab6b42cf5bb36f56badde2aaafc3807f03f781d00e7861a/granian-2.7.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a052ed466da5922cb443435a95a0c751566943278a6f22cef3d2e19d4e7ecdea", size = 7048915, upload-time = "2026-02-24T23:02:50.773Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ab/bc/cf0bc29f583096a842cf0f26ae2fe40c72ed5286d4548be99ecfcdbb17e2/granian-2.7.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:76b840ff13dde8838fd33cd096f2e7cadf2c21a499a67f695f53de57deab6ff8", size = 6440868, upload-time = "2026-02-24T23:02:53.619Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2f/0d/bae1dcd2182ba5d9a5df33eb50b56dc5bbe67e31033d822e079aa8c1ff30/granian-2.7.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:00ccc8d7284bc7360f310179d0b4d17e5ca3077bbe24427e9e9310df397e3831", size = 6097336, upload-time = "2026-02-24T23:02:55.185Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/65/7d/3e0a7f32b0ad5faa1d847c51191391552fa239821c95fc7c022688985df2/granian-2.7.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:675987c1b321dc8af593db8639e00c25277449b32e8c1b2ddd46b35f28d9fac4", size = 7098742, upload-time = "2026-02-24T23:02:57.898Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/89/41/3b44386d636ac6467f0f13f45474c71fc3b90a4f0ba8b536de91b2845a09/granian-2.7.2-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:681c6fbe3354aaa6251e6191ec89f5174ac3b9fbc4b4db606fea456d01969fcb", size = 6430667, upload-time = "2026-02-24T23:02:59.789Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/52/70/7b24e187aed3fb7ac2b29d2480a045559a509ef9fec54cffb8694a2d94af/granian-2.7.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e5c9ae65af5e572dca27d8ca0da4c5180b08473ac47e6f5329699e9455a5cc3", size = 6948424, upload-time = "2026-02-24T23:03:01.406Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/fa/4c/cb74c367f9efb874f2c8433fe9bf3e824f05cf719f2251d40e29e07f08c0/granian-2.7.2-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:e37fab2be919ceb195db00d7f49ec220444b1ecaa07c03f7c1c874cacff9de83", size = 7000407, upload-time = "2026-02-24T23:03:03.214Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/58/98/dfed3966ed7fbd3aae56e123598f90dc206484092b8373d0a71e2d8b82a8/granian-2.7.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:8ec167ab30f5396b5caaff16820a39f4e91986d2fe5bdc02992a03c2b2b2b313", size = 7121626, upload-time = "2026-02-24T23:03:05.349Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/39/82/acec732a345cd03b2f6e48ac04b66b7b8b61f5c50eb08d7421fc8c56591a/granian-2.7.2-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:63f426d793f2116d23be265dd826bec1e623680baf94cc270fe08923113a86ba", size = 7253447, upload-time = "2026-02-24T23:03:06.986Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c5/2b/64779e69b08c1ff1bfc09a4ede904ab761ff63f936c275710886057c52f7/granian-2.7.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:1617cbb4efe3112f07fb6762cf81d2d9fe4bdb78971d1fd0a310f8b132f6a51e", size = 7053005, upload-time = "2026-02-24T23:03:09.021Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4c/49/9eb88875d709db7e7844e1c681546448dab5ff5651cd1c1d80ac4b1de4e3/granian-2.7.2-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:016c5857c8baedeab7eb065f98417f5ea26bb72b0f7e0544fe76071efc5ab255", size = 6401748, upload-time = "2026-02-24T23:03:12.802Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e3/80/85726ad9999ed89cb6a32f7f57eb50ce7261459d9c30c3b194ae4c5aa2c5/granian-2.7.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:dcbe01fa141adf3f90964e86a959e250754aa7c6dad8fa7a855e6fd382de4c13", size = 6101265, upload-time = "2026-02-24T23:03:14.435Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/07/82/0df56a42b9f4c327d0e0b052f43369127e1b565b9e66bf2c9488f1c8d759/granian-2.7.2-cp313-cp313t-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:283ba23817a685784b66f45423d2f25715fdc076c8ffb43c49a807ee56a0ffc0", size = 6249488, upload-time = "2026-02-24T23:03:16.387Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ef/cc/d83a351560a3d6377672636129c52f06f8393f5831c5ee0f06f274883ea6/granian-2.7.2-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3258419c741897273ce155568b5a9cbacb7700a00516e87119a90f7d520d6783", size = 7104734, upload-time = "2026-02-24T23:03:17.993Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/84/d1/539907ee96d0ee2bcceabb4a6a9643b75378d6dfea09b7a9e4fd22cdf977/granian-2.7.2-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a196125c4837491c139c9cc83541b48c408c92b9cfbbf004fd28717f9c02ad21", size = 6785504, upload-time = "2026-02-24T23:03:19.763Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/86/bf/4b6f45882f8341e7c6cb824d693deb94c306be6525b483c76fb373d1e749/granian-2.7.2-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:746555ac8a2dcd9257bfe7ad58f1d7a60892bc4613df6a7d8f736692b3bb3b88", size = 6902790, upload-time = "2026-02-24T23:03:22.215Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/44/b8/832970d2d4b144b87be39f5b9dfd31fdb17f298dc238a0b2100c95002cf8/granian-2.7.2-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:5ac1843c6084933a54a07d9dcae643365f1d83aaff3fd4f2676ea301185e4e8b", size = 7082682, upload-time = "2026-02-24T23:03:23.875Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/38/bc/1521dbf026d1c9d2465cd54e016efd8ff6e1e72eff521071dab20dd61c44/granian-2.7.2-cp313-cp313t-musllinux_1_1_armv7l.whl", hash = "sha256:3612eb6a3f4351dd2c4df246ed0d21056c0556a6b1ed772dd865310aa55a9ba9", size = 7264742, upload-time = "2026-02-24T23:03:25.562Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/19/ae/00884ab77045a2f54db90932f9d1ca522201e2a6b2cf2a9b38840db0fd54/granian-2.7.2-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:34708b145e31b4538e0556704a07454a76d6776c55c5bc3a1335e80ef6b3bae3", size = 7062571, upload-time = "2026-02-24T23:03:27.278Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/69/4a/8ce622f4f7d58e035d121b9957dd5a8929028dc99cfc5d2bf7f2aa28912c/granian-2.7.2-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:592806c28c491f9c1d1501bac706ecf5e72b73969f20f912678d53308786d658", size = 6442041, upload-time = "2026-02-24T23:03:30.986Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/27/62/7d36ed38a40a68c2856b6d2a6fedd40833e7f82eb90ba0d03f2d69ffadf5/granian-2.7.2-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c9dcde3968b921654bde999468e97d03031f28668bc1fc145c81d8bedb0fb2a4", size = 6100793, upload-time = "2026-02-24T23:03:32.734Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b4/c5/17fea68f4cb280c217cbd65534664722c9c9b0138c2754e20c235d70b5f4/granian-2.7.2-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6d4d78408283ec51f0fb00557856b4593947ad5b48287c04e1c22764a0ac28a5", size = 7119810, upload-time = "2026-02-24T23:03:34.807Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/76/35e240d107e0f158662652fd61191de4fb0c2c080e3786ca8f16c71547b7/granian-2.7.2-cp314-cp314-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:66d28b078e8087f794b83822055f95caf93d83b23f47f4efcd5e2f0f7a5d8a81", size = 6450789, upload-time = "2026-02-24T23:03:36.81Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4c/55/a6d08cfecc808149a910e51c57883ab26fad69d922dc2e76fb2d87469e2d/granian-2.7.2-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4ff7a93123ab339ba6cad51cc7141f8880ec47b152ce2491595bb08edda20106", size = 6902672, upload-time = "2026-02-24T23:03:38.655Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/98/2e/c86d95f324248fcc5dcaf034c9f688b32f7a488f0b2a4a25e6673776107f/granian-2.7.2-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:a52effb9889f0944f0353afd6ce5a9d9aa83826d44bbf3c8013e978a3d6ef7b7", size = 6964399, upload-time = "2026-02-24T23:03:40.459Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/37/4b/44fde33fe10245a3fba76bf843c387fad2d548244345115b9d87e1c40994/granian-2.7.2-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:76c987c3ca78bf7666ab053c3ed7e3af405af91b2e5ce2f1cf92634c1581e238", size = 7034929, upload-time = "2026-02-24T23:03:42.149Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/90/76/38d205cb527046241a9ee4f51048bf44101c626ad4d2af16dd9d14dc1db6/granian-2.7.2-cp314-cp314-musllinux_1_1_armv7l.whl", hash = "sha256:6590f8092c2bb6614e561ba771f084cbf72ecbc38dbf9849762ac38718085c29", size = 7259609, upload-time = "2026-02-24T23:03:43.852Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/00/37/04245c7259e65f1083ce193875c6c44da4c98604d3b00a264a74dd4f042b/granian-2.7.2-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:7c1ce9b0c9446b680e9545e7fc95a75f0c53a25dedcf924b1750c3e5ba5bf908", size = 7073161, upload-time = "2026-02-24T23:03:45.655Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/cc/07/0e56fb4f178e14b4c1fa1f6f00586ca81761ccbe2d8803f2c12b6b17a7d6/granian-2.7.2-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:a698d9b662d5648c8ae3dc01ad01688e1a8afc3525e431e7cddb841c53e5e291", size = 6415279, upload-time = "2026-02-24T23:03:48.932Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/27/bc/3e69305bf34806cd852f4683deec844a2cb9a4d8888d7f172b507f6080a8/granian-2.7.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:17516095b520b3c039ddbe41a6beb2c59d554b668cc229d36d82c93154a799af", size = 6090528, upload-time = "2026-02-24T23:03:50.52Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ec/10/7d58a922b44417a6207c0a3230b0841cd7385a36fc518ac15fed16ebf6f7/granian-2.7.2-cp314-cp314t-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:96b0fd9eac60f939b3cbe44c8f32a42fdb7c1a1a9e07ca89e7795cdc7a606beb", size = 6252291, upload-time = "2026-02-24T23:03:52.248Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/54/56/65776c6d759dcef9cce15bc11bdea2c64fe668088faf35d87916bd88f595/granian-2.7.2-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e50fb13e053384b8bd3823d4967606c6fd89f2b0d20e64de3ae212b85ffdfed2", size = 7106748, upload-time = "2026-02-24T23:03:53.994Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/81/ee/d9ed836316607401f158ac264a3f770469d1b1edbf119402777a9eff1833/granian-2.7.2-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9bb1ef13125bc05ab2e18869ed311beaeb085a4c4c195d55d0865f5753a4c0b4", size = 6778883, upload-time = "2026-02-24T23:03:55.574Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a1/46/eabab80e07a14527c336dec6d902329399f3ba2b82dc94b6435651021359/granian-2.7.2-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:b1c77189335070c6ba6b8d158518fde4c50f892753620f0b22a7552ad4347143", size = 6903426, upload-time = "2026-02-24T23:03:57.296Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/24/8a/8ce186826066f6d453316229383a5be3b0b8a4130146c21f321ee64fe2cb/granian-2.7.2-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:1777166c3c853eed4440adb3cbbf34bba2b77d595bfc143a5826904a80b22f34", size = 7083877, upload-time = "2026-02-24T23:03:59.425Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/cf/eb/91ed4646ce1c920ad39db0bcddb6f4755e1823002b14fb026104e3eb8bce/granian-2.7.2-cp314-cp314t-musllinux_1_1_armv7l.whl", hash = "sha256:0ffac19208ae548f3647c849579b803beaed2b50dfb0f3790ad26daac0033484", size = 7267282, upload-time = "2026-02-24T23:04:01.218Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/49/2f/58cba479254530ab09132e150e4ab55362f6e875d9e82b6790477843e0aa/granian-2.7.2-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:82f34e78c1297bf5a1b6a5097e30428db98b59fce60a7387977b794855c0c3bc", size = 7054941, upload-time = "2026-02-24T23:04:03.211Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/59/71/f21b26c7dc7a8bc9d8288552c9c12128e73f1c3f04799b6e28a0a269b9b0/granian-2.7.2-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5613ee8c1233a79e56e1735e19c8c70af22a8c6b5808d7c1423dc5387bee4c05", size = 6504773, upload-time = "2026-02-24T23:04:06.498Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6e/68/282fbf5418f9348f657f505dc744cdca70ac850d39a805b21395211bf099/granian-2.7.2-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:0cd6fee79f585de2e1a90b6a311f62b3768c7cda649bc0e02908157ffa2553cc", size = 6138096, upload-time = "2026-02-24T23:04:09.138Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e7/e0/b578709020f84c07ad2ca88f77ac67fd2c62e6b16f93ff8c8d65b7d99296/granian-2.7.2-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e94c825f8b327114f7062d158c502a540ef5819f809e10158f0edddddaf41bb9", size = 6900043, upload-time = "2026-02-24T23:04:11.015Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/2f/a2671cc160f29ccf8e605eb8fa113c01051b0d7947048c5b29eb4e603384/granian-2.7.2-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:a6adea5fb8a537d18f3f2b848023151063bc45896415fdebfeb0bf0663d5a03b", size = 7040211, upload-time = "2026-02-24T23:04:13.31Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/36/ce/df9bba3b211cda2d47535bb21bc040007e021e8c8adc20ce36619f903bc4/granian-2.7.2-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:2392ab03cb92b1b2d4363f450b2d875177e10f0e22d67a4423052e6885e430f2", size = 7118085, upload-time = "2026-02-24T23:04:15.05Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a9/87/37124b2ee0cddce6ba438b0ff879ddae094ae2c92b24b28ffbe35110931f/granian-2.7.2-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:406c0bb1f5bf55c72cfbfdfd2ccec21299eb3f7b311d85c4889dde357fd36f33", size = 7314667, upload-time = "2026-02-24T23:04:16.783Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8c/ac/8b142ed352bc525e3c97440aab312928beebc735927b0cf979692bfcda3b/granian-2.7.2-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:362a6001daa2ce62532a49df407fe545076052ef29289a76d5760064d820f48b", size = 7004934, upload-time = "2026-02-24T23:04:19.059Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/28/a3ee3f2220c0b9045f8caa2a2cb7484618961b7500f88594349a7889d391/granian-2.7.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:e76afb483d7f42a0b911bdb447d282f70ad7a96caabd4c99cdc300117c5f8977", size = 4580966, upload-time = "2026-02-02T11:38:14.077Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1b/60/b53da9c255f6853a5516d0f8a3e7325c24123f0f7e77856558c49810f4ce/granian-2.7.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:628523302274f95ca967f295a9aa7bc4ade5e1eced42afc60d06dfe20f2da07a", size = 4210344, upload-time = "2026-02-02T11:38:15.34Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a2/bb/c3380106565bc99edfb90baafa1a8081a4334709ce0200d207ddda36275e/granian-2.7.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a62560b64a17e1cbae61038285d5fa8a32613ada9a46f05047dc607ea7d38f23", size = 5130258, upload-time = "2026-02-02T11:38:17.175Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a2/8f/2c3348d6d33807e3b818ac07366b5251e811ce2548fbe82e0b55982d8a13/granian-2.7.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:47b8e0e9497d24466d6511443cc18f22f18405aab5a7e2fece1dd38206af88c4", size = 4576496, upload-time = "2026-02-02T11:38:18.577Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f6/71/d1d146170a23f3523d8629b47f849b30ba0d513eb519188ce5d7bfd1b916/granian-2.7.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc6039c61a07b2d36462c487b66b131ae3fd862bdc8fb81d6e5c206c1a2b683c", size = 4975062, upload-time = "2026-02-02T11:38:20.084Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/16/f9/f3acbf8c41cd10ff81109bd9078d3228f23e52bab8673763c65739a87e30/granian-2.7.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:f3b0442beb11b035ee09959726f44b3730d0b55688110defd1d9a9a6c7486955", size = 4827755, upload-time = "2026-02-02T11:38:21.817Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9f/f8/503135b89539feea2be495b47858c22409ba77ffcb71920ae0727c674189/granian-2.7.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:741d0b58a5133cc5902b3129a8a4c55143f0f8769a80e7aa80caadc64c9f1d8b", size = 4939033, upload-time = "2026-02-02T11:38:23.033Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/99/90/aaabe2c1162d07a6af55532b6f616199aa237805ef1d732fa78d9883d217/granian-2.7.0-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:02a6fe6a19f290b70bc23feeb3809511becdaff2263b0469f02c28772af97652", size = 5292980, upload-time = "2026-02-02T11:38:24.823Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/eb/aa/d1eb7342676893ab0ec1e66cceca4450bec3f29c488db2a92af5b4211d4d/granian-2.7.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8239b1a661271428c3e358e4bdcaaaf877a432cc593e93fc6b5a612ae521b06a", size = 5087230, upload-time = "2026-02-02T11:38:26.09Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/97/1a/b6d7840bfd9cd9bed627b138e6e8e49d1961997adba30ee39ad75d07ed58/granian-2.7.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:d9c42562dcbf52848d0a9d0db58f8f2e790586eb0c363b8ad1b30fe0bd362117", size = 4572728, upload-time = "2026-02-02T11:38:30.143Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/15/93/f8f7224d9eaaaf4dbf493035a85287fa2e27c17e5f7aacc01821d8aa66b4/granian-2.7.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a3421bd5c90430073e1f3f88fc63bc8d0a8ee547a9a5c06d577a281f384160bd", size = 4195034, upload-time = "2026-02-02T11:38:32.007Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4b/db/66843a35e1b6345da2a1c71839fb9aa7eb0f17d380fbf4cb5c7e06eb6f85/granian-2.7.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8b8057dc81772932e208f2327b5e347459eb78896118e27af9845801e267cec5", size = 5123768, upload-time = "2026-02-02T11:38:33.449Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/10/ce/631c5c1f7a4e6b8c98ec857b3e6795fe64e474b6f48df388ac701a21f3fe/granian-2.7.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1e5e70f438b1a4787d76566770e98bf7732407efa02802f38f10c960247107d7", size = 4562424, upload-time = "2026-02-02T11:38:34.815Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/28/41/19bdfa3719e22c4dcf6fa1a53323551a37aa58a4ca7a768db6a0ba714ab0/granian-2.7.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:213dd224a47c7bfcbb91718c7eeb56d6067825a28dcae50f537964e2dafb729a", size = 5006002, upload-time = "2026-02-02T11:38:36.76Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3c/5b/3b40f489e2449eb58df93ad38f42d1a6c2910502a4bc8017c047e16d637c/granian-2.7.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:bb5be27c0265268d43bab9a878ac27a20b4288843ffc9fda1009b8226673f629", size = 4825073, upload-time = "2026-02-02T11:38:37.998Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/04/92/b6de6f8c4146409efb58aee75277b810d54de03a1687d33f1f3f1feb3395/granian-2.7.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a6ff95aede82903c06eb560a32b10e9235fdafc4568c8fe7dcac28d62be5ffa2", size = 4928628, upload-time = "2026-02-02T11:38:39.481Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/39/21/d8a191dcfbf8422b868ab847829670075ba3e4325611e0a9fd2dc909a142/granian-2.7.0-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:e44f0c1676b27582df26d47cf466fedebd72f520edc2025f125c83ff58af77f9", size = 5282898, upload-time = "2026-02-02T11:38:40.815Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d0/46/2746f1a4f0f093576fb64b63c3f022f254c6d2c4cc66d37dd881608397ce/granian-2.7.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:9241b72f95ceb57e2bbce55e0f61c250c1c02e9d2f8531b027dd3dc204209fdd", size = 5118453, upload-time = "2026-02-02T11:38:42.716Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f8/df/b68626242fb4913df0968ee5662f5a394857b3d6fc4ee17c94be69664491/granian-2.7.0-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:bc61451791c8963232e4921c6805e7c2e366635e1e658267b1854889116ff6d7", size = 4572200, upload-time = "2026-02-02T11:38:46.194Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c0/15/2fe28bca0751d9dc46e5c7e9e4b0c4fd1a55e3e8ba062f28292322ee160b/granian-2.7.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e274a0d6a01c475b9135212106ca5b69f5ec2f67f4ca6ce812d185d80255cdf5", size = 4195415, upload-time = "2026-02-02T11:38:47.78Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/07/2a/d4dc40e58a55835cac5296f5090cc3ce2d43332ad486bbf78b3a00e46199/granian-2.7.0-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:34bd28075adae3453c596ee20089e0288379e3fdf1cec8bafff89bb175ea0eb4", size = 5122981, upload-time = "2026-02-02T11:38:49.55Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bd/fe/8c79837df620dc0eca6a8b799505910cbba2d85d92ccc58d1c549f7027be/granian-2.7.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f526583b72cf9e6ca9a4849c781ed546f44005f0ad4b5c7eb1090e1ebec209bf", size = 4561440, upload-time = "2026-02-02T11:38:50.799Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4f/e7/d7abfaa9829ff50cddc27919bd3ce5a335402ebbbaa650e96fe579136674/granian-2.7.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95ac07d5314e03e667210349dfc76124d69726731007c24716e21a2554cc15ca", size = 5005076, upload-time = "2026-02-02T11:38:52.157Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1a/45/108afaa0636c93b6a8ff12810787e4a1ea27fffe59f12ca0de7c784b119a/granian-2.7.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:f6812e342c41ca80e1b34fb6c9a7e51a4bbd14f59025bd1bb59d45a39e02b8d5", size = 4825142, upload-time = "2026-02-02T11:38:53.506Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4b/eb/cedf4675b1047490f819ce8bd1ee1ea74b6c772ae9d9dd1c117ae690a3eb/granian-2.7.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:7a4099ba59885123405699a5313757556ff106f90336dccdf4ceda76f32657d0", size = 4927830, upload-time = "2026-02-02T11:38:54.92Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f9/b5/2d7a2e03ba29a6915ad41502e2870899b9eb54861e3d06ad8470c5e70b41/granian-2.7.0-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:c487731fbae86808410e88c587eb4071213812c5f52570b7981bf07a1b84be25", size = 5282142, upload-time = "2026-02-02T11:38:56.445Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a9/e7/c851b2e2351727186b4bc4a35df832e2e97e4f77b8a93dfdb6daa098cf9e/granian-2.7.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ca4877ebf8873488ba72a299206621bd0c6febb8f091f3da62117c1fe344501f", size = 5117907, upload-time = "2026-02-02T11:38:57.852Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e1/2f/c9bcd4aa36d3092fe88a623e60aa89bd4ff16836803a633b8b454946a845/granian-2.7.0-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:e1df8e4669b4fb69b373b2ab40a10a8c511eeb41838d65adb375d1c0e4e7454c", size = 4493110, upload-time = "2026-02-02T11:39:01.294Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6a/b4/02d11870255920d35f8eab390e509d3688fe0018011bb606aa00057b778f/granian-2.7.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:6331ed9d3eb06cfba737dfb8efa3f0a8b4d4312a5af91c0a67bfbaa078b62eb4", size = 4122388, upload-time = "2026-02-02T11:39:02.509Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/98/50/dfad5a414a2e3e14c30cd0d54cef1dab4874a67c1e6f8b1124d9998ed8b2/granian-2.7.0-cp313-cp313t-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:093e1c277eddba00eaa94ca82ff7a9ab57b0554cd7013e5b2f3468635dbe520d", size = 4379344, upload-time = "2026-02-02T11:39:04.489Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6e/53/ef086af03ef31aa3c1dbff2da5928a9b5dd1f48d8ebee18dd6628951ae9e/granian-2.7.0-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8e8e317bdc9ca9905d0b20f665f8fe31080c7f13d90675439113932bb3272c24", size = 5069172, upload-time = "2026-02-02T11:39:05.757Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c3/57/117864ea46c6cbcbeff733a4da736e814b06d6634beeb201b9db176bd6be/granian-2.7.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:391e8589265178fd7f444b6711b6dda157a6b66059a15bf1033ffceeaf26918c", size = 4848246, upload-time = "2026-02-02T11:39:07.048Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/60/da/2d45b7b6638a77362228d6770a61fa2bc3feae6c52a80993c230f344b197/granian-2.7.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:49b6873f4a8ee7a1ea627ff98d67ecdd644cfc18aab475b2e15f651dbcbe4140", size = 4669023, upload-time = "2026-02-02T11:39:09.612Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/22/69/49e54eb6ed67ccf471c19d4c65f64197dd5a416d501620519e28ea92c82e/granian-2.7.0-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:39778147c7527de0bcda12cd9c38863d4e6a80d3a8a96ddeb6fe2d1342f337db", size = 4896002, upload-time = "2026-02-02T11:39:10.996Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c5/f1/a864a78029265d06a6fd61c760c8facf032be0d345deca5081718cbb006f/granian-2.7.0-cp313-cp313t-musllinux_1_1_armv7l.whl", hash = "sha256:8135d0a4574dc5a0acf3a815fc6cad5bbe9075ef86df2c091ec34fbd21639c1c", size = 5239945, upload-time = "2026-02-02T11:39:12.726Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/26/33/feef40e4570b771d815c1ddd1008ccc9c0e81ce5a015deded6788e919f18/granian-2.7.0-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:47df2d9e50f22fa820b34fd38ceeeedc0b97994fa164425fa30e746759db8a44", size = 5078968, upload-time = "2026-02-02T11:39:14.048Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b9/6a/b8d58474bbcbca450f030fd41b65c94ae0afb5e8f58c39fbea2df4efee2b/granian-2.7.0-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:23c6531b75c94c7b533812aed4f40dc93008c406cfa5629ec93397cd0f6770cb", size = 4569780, upload-time = "2026-02-02T11:39:16.671Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c2/dc/a8b11425ebdf6cb58e1084fdb7759d853ca7f0b00376e4bb66300322f5d3/granian-2.7.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:e4939b86f2b7918202ce56cb01c2efe20a393c742d41640b444e82c8b444b614", size = 4195285, upload-time = "2026-02-02T11:39:18.596Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/b5/6cc0b94f997d93f4b1510b2d953f07a7f1d16a143d60b53e0e50b887fa12/granian-2.7.0-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:38fa10adf3c4d50e31a08401e6701ee2488613d905bb316cad456e5ebad5aa81", size = 5121311, upload-time = "2026-02-02T11:39:20.092Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f4/f9/df3d862874cf4b233f97253bb78991ae4f31179a5581beaa41a2100e3bce/granian-2.7.0-cp314-cp314-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9b366a9fd713a20321e668768b122b7b0140bfaeb3cb0557b6cb11dce827a4fb", size = 4557737, upload-time = "2026-02-02T11:39:21.992Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/7f/e3063368345f39188afe5baa1ab62fdd951097656cd83bec3964f91f6e66/granian-2.7.0-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a916413e0dcd5c6eaf7f7413a6d899f7ba53a988d08e3b3c7ab2e0b5fa687559", size = 5004108, upload-time = "2026-02-02T11:39:23.306Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bc/eb/892bcc0cfc44ed791795bab251e0b6ed767397182bac134d9f0fcecc552e/granian-2.7.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:e315adf24162294d35ca4bed66c8f66ac15a0696f2cb462e729122d148f6d958", size = 4823143, upload-time = "2026-02-02T11:39:24.696Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b3/e0/ff8528bf620b6da7833171f6d30bfe4b4b1d6e7d155b634bd17590e0c4b4/granian-2.7.0-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:486f8785e716f76f96534aaba25acd5dee1a8398725ffd2a55f0833689c75933", size = 4926328, upload-time = "2026-02-02T11:39:26.111Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/02/f7/fb0a761d39245295660703a42e9448f3c04ce1f26b2f62e044d179167880/granian-2.7.0-cp314-cp314-musllinux_1_1_armv7l.whl", hash = "sha256:0e5e2c1c6ff1501e3675e5237096b90b767f506bb0ef88594310b7b9eaa95532", size = 5281190, upload-time = "2026-02-02T11:39:27.68Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d6/d8/860e7e96ea109c6db431c8284040d265758bded35f9ce2de05f3969d7c0c/granian-2.7.0-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:d4418b417f9c2162b4fa9ec41ec34ed3e8ed891463bb058873034222be53542f", size = 5117989, upload-time = "2026-02-02T11:39:29.008Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/fb/9a/500ab01ae273870e8fc056956cc49716707b4a0e76fb2b5993258e1494f7/granian-2.7.0-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:b4367c088c00bdc38a8a495282070010914931edb4c488499f290c91018d9e80", size = 4492656, upload-time = "2026-02-02T11:39:31.614Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d0/26/86dc5a6fff60ee0cc38c2fcd1a0d4cebd52e6764a9f752a20458001ca57e/granian-2.7.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:c8f3df224284ed1ff673f61de652337d7721100bf4cfc336b2047005b0edb2e0", size = 4122201, upload-time = "2026-02-02T11:39:33.162Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/60/887dc5a099135ff449adcdea9a2aa38f39673baf99de9acb78077b701432/granian-2.7.0-cp314-cp314t-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6682c08b0d82ad75f8e9d1571254630133e1563c49f0600c2e2dc26cec743ae7", size = 4377489, upload-time = "2026-02-02T11:39:34.532Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5a/6b/68c12f8c4c1f1c109bf55d66beeb37a817fd908af5d5d9b48afcbdc3e623/granian-2.7.0-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d6ccc3bdc2248775b6bd292d7d37a1bff79eb1aaf931f3a217ea9fb9a6fe7ca4", size = 5067294, upload-time = "2026-02-02T11:39:35.84Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ff/4f/be4f9c129f5f80f52654f257abe91f647defec020fa134b3600013b7219d/granian-2.7.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5431272a4d6f49a200aeb7b01010a3785b93b9bd8cd813d98ed29c8e9ba1c476", size = 4848356, upload-time = "2026-02-02T11:39:37.443Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d7/aa/f6efcfb435f370a6f3626bd5837465bfb71950f6b3cb3c74e54b176c72e2/granian-2.7.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:790b150255576775672f26dbcbd6eb05f70260dd661b91ce462f6f3846db9501", size = 4669022, upload-time = "2026-02-02T11:39:38.782Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1d/36/e86050c476046ef1f0aae0eb86d098fa787abfc8887a131c82baccc7565e/granian-2.7.0-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:ce9be999273c181e4b65efbbd82a5bc6f223f1db3463660514d1dc229c8ba760", size = 4895567, upload-time = "2026-02-02T11:39:40.144Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2b/5e/25283ff7fc12fcf42ae8a5687243119739cf4b0bf5ccb1c32d11d37987b1/granian-2.7.0-cp314-cp314t-musllinux_1_1_armv7l.whl", hash = "sha256:319b34f18ed3162354513acb5a9e8cee720ac166cd88fe05f0f057703eb47e4f", size = 5238652, upload-time = "2026-02-02T11:39:41.648Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5f/60/06148781120e086c7437aa9513198025ea1eb847cb2e244d5e2b9801782e/granian-2.7.0-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:b01bed8ad748840e7ab49373f642076f3bc459e39937a4ce11c5be03e67cdfd9", size = 5079018, upload-time = "2026-02-02T11:39:43.309Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/0b/39ebf1b791bbd4049239ecfee8f072321211879e5617a023921961be1d55/granian-2.7.0-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:24a1f6a894bea95ef0e603bebacbccd19c319c0da493bb4fde8b94b8629f3dc8", size = 4581648, upload-time = "2026-02-02T11:39:45.991Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2f/cd/4642192520478bba4cd547124d92607c958a0786864ebe378f3008b40048/granian-2.7.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:c2799497ac896cffea85512983c5d9eb4ae51ebacd7a9a5fd3d2ac81f1755fac", size = 4214257, upload-time = "2026-02-02T11:39:47.507Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e2/3f/615f93753c3b682219fe546196fc9eb3a045d846e57883312c97de4d785a/granian-2.7.0-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b66a15d004136e641706e0e5522b3509151e2027a0677cf4fa97d049d9ddfa41", size = 4979656, upload-time = "2026-02-02T11:39:48.838Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6e/68/1f2c36a964f93bfe8d6189431b8425acc591b735e47d8898b2e70c478398/granian-2.7.0-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:de5a6fa93d2138ba2372d20d97b87c1af75fa16a59a93841745326825c3ddf83", size = 4844448, upload-time = "2026-02-02T11:39:50.5Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/df/23/d8c83fe6a6656026c734c2ea771cbcdec6f0010e749f8ab0db1bfc8a3dfe/granian-2.7.0-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:aacda2ad46724490c4cd811b8dcadff2260603a3e95ca0d8c33552d791a3c6ac", size = 4930755, upload-time = "2026-02-02T11:39:51.866Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/20/e5/2a86ee18544185e72fc50b50985b6bfb4504f7835875d2636f573e100071/granian-2.7.0-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:7efb5ebdb308ed1685a80cded6ea51447753e8afe92c21fc3abf9a06a9eb5d2e", size = 5295728, upload-time = "2026-02-02T11:39:53.364Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/bd/0d47d17769601c56d876b289456f27799611571227b99ad300e221600bbd/granian-2.7.0-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:ae96b75420d01d9a7dbe1bd84f1898b2b0ade6883db59bfe2b233d7c28c6b0df", size = 5095149, upload-time = "2026-02-02T11:39:54.767Z" },
|
||||
]
|
||||
|
||||
[package.optional-dependencies]
|
||||
|
||||
Reference in New Issue
Block a user