Replace list_missing_pages/list_removed_paths with a comm(1)-based diff

The docset Makefile's list_missing_pages ran one sqlite3 query per
mkdocs page, and list_removed_paths nested a loop over all mkdocs pages
inside a loop over all docset index paths (O(n*m) shell iteration).
Issue #5718 item 5 suggested removing or reducing these targets once
#5638's check_docset() lands, but that PR is still open and covers only
API pages and macros, not the full page set these targets check.
Replace the loops with two sorted path lists (DOCSET_PAGE_PATHS from
mkdocs' markdown sources, DOCSET_INDEX_PATHS from the built docset
index) compared with a single comm(1) call each, verified to produce
output identical to the old loops against the current docSet.dsidx.

The sed expression used '#' as its delimiter, which GNU Make reads as
a comment character even inside a variable assignment, truncating the
line and orphaning the closing paren of $(shell ...) ("unterminated
call to function 'shell': missing ')'"). Use '@' as the delimiter
instead.

Part of #5718 item 5

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

.github/workflows/publish_documentation.yml

@@ -7,6 +7,16 @@ on:
       - develop
     paths:
       - docs/mkdocs/**
+      # the site also embeds these files via pymdownx.snippets
+      # (mkdocs.yml sets restrict_base_path: false for this)
+      - .clang-tidy
+      - .github/CODE_OF_CONDUCT.md
+      - .github/CONTRIBUTING.md
+      - .github/SECURITY.md
+      - cmake/clang_flags.cmake
+      - cmake/gcc_flags.cmake
+      - tests/fmt_formatter/project/main.cpp
+      - tools/astyle/.astylerc
   workflow_dispatch:
 
 # we don't want to have concurrent jobs, and we don't want to cancel running jobs to avoid broken publications
@@ -23,7 +33,7 @@ jobs:
       contents: write
 
     if: github.repository == 'nlohmann/json'
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
         uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
@@ -31,6 +41,8 @@ jobs:
           egress-policy: audit
 
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
 
       - name: Install virtual environment
         run: make install_venv -C docs/mkdocs

.github/workflows/ubuntu.yml

@@ -346,6 +346,8 @@ jobs:
     container: intel/oneapi-hpckit:latest
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
       - name: Get latest CMake and ninja
         uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
@@ -358,6 +360,8 @@ jobs:
     container: nvcr.io/nvidia/nvhpc:25.5-devel-cuda12.9-ubuntu22.04
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
       - name: Get latest CMake and ninja
         uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake

.github/workflows/windows.yml

@@ -87,6 +87,8 @@ jobs:
 
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
       - name: Get latest CMake and ninja
         uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Set extra CXX_FLAGS for latest std_version
@@ -123,6 +125,8 @@ jobs:
 
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
       - name: Run CMake (Release)
         run: cmake -S . -B build -G "Visual Studio 18 2026" -A ARM64 -DJSON_BuildTests=On -DCMAKE_CXX_FLAGS="/W4 /WX"
         if: matrix.build_type == 'Release'

docs/Makefile

@@ -11,20 +11,31 @@ EXAMPLES = $(wildcard mkdocs/docs/examples/*.cpp)
 
 cxx_standard = $(lastword c++11 $(filter c++%, $(subst ., ,$1)))
 
+# common compile flags for the stand-alone example files
+EXAMPLE_CPPFLAGS = -I $(SRCDIR) -DJSON_USE_GLOBAL_UDLS=0
+EXAMPLE_WARNFLAGS = -Werror=deprecated-declarations
+
+# examples that document deprecated API and are allowed to use it
+DEPRECATED_EXAMPLES = $(addprefix mkdocs/docs/examples/, \
+	json_pointer__operator__equal_stringtype \
+	json_pointer__operator__notequal_stringtype \
+	json_pointer__operator_string_t)
+$(DEPRECATED_EXAMPLES:=.output) $(DEPRECATED_EXAMPLES:=.test): EXAMPLE_WARNFLAGS = -Wno-deprecated-declarations
+
 # create output from a stand-alone example file
 %.output: %.cpp
-	@echo "standard $(call cxx_standard $(<:.cpp=))"
+	@echo "standard $(call cxx_standard,$(<:.cpp=))"
 	$(MAKE) $(<:.cpp=) \
-		CPPFLAGS="-I $(SRCDIR) -DJSON_USE_GLOBAL_UDLS=0" \
+		CPPFLAGS="$(EXAMPLE_CPPFLAGS)" \
-		CXXFLAGS="-std=$(call cxx_standard,$(<:.cpp=)) -Wno-deprecated-declarations"
+		CXXFLAGS="-std=$(call cxx_standard,$(<:.cpp=)) $(EXAMPLE_WARNFLAGS)"
 	./$(<:.cpp=) > $@
 	rm $(<:.cpp=)
 
 # compare created output with current output of the example files
 %.test: %.cpp
 	$(MAKE) $(<:.cpp=) \
-		CPPFLAGS="-I $(SRCDIR) -DJSON_USE_GLOBAL_UDLS=0" \
+		CPPFLAGS="$(EXAMPLE_CPPFLAGS)" \
-		CXXFLAGS="-std=$(call cxx_standard,$(<:.cpp=)) -Wno-deprecated-declarations"
+		CXXFLAGS="-std=$(call cxx_standard,$(<:.cpp=)) $(EXAMPLE_WARNFLAGS)"
 	./$(<:.cpp=) > $@
 	diff $@ $(<:.cpp=.output)
 	rm $(<:.cpp=) $@

docs/docset/Info.plist

@@ -13,7 +13,7 @@
     <key>dashIndexFilePath</key>
     <string>index.html</string>
     <key>DashDocSetFallbackURL</key>
-    <string>https://nlohmann.github.io/json/</string>
+    <string>https://json.nlohmann.me/</string>
     <key>isJavaScriptEnabled</key>
     <true/>
 </dict>

docs/docset/Makefile

@@ -52,35 +52,25 @@ install_docset_zeal: JSON_for_Modern_C++.docset
 	mkdir -p $$docset_root; \
 	cp -r JSON_for_Modern_C++.docset $$docset_root/
 
+# both targets below compare the docset search index with the mkdocs page
+# set. They share the same normalization (docs/foo/index.md and
+# docs/foo.md both become foo/index.html, the URL mkdocs itself would
+# give the page; the top-level index.md is excluded, as it is not part
+# of the hand-curated docSet.sql) and use comm(1) on two sorted lists
+# instead of running a sqlite3 query, or an O(n*m) nested shell loop,
+# once per page.
+DOCSET_INDEX_PATHS=$(shell sqlite3 docSet.dsidx "SELECT DISTINCT path FROM searchIndex" | sort)
+DOCSET_PAGE_PATHS=$(shell echo '$(MKDOCS_PAGES)' | tr ' ' '\n' | grep -v '^index\.md$$' | $(SED) -E 's@/index\.md$$@/index.html@; s@\.md$$@/index.html@' | sort)
+
 # list mkdocs pages missing from the docset index
 .PHONY: list_missing_pages
 list_missing_pages: docSet.dsidx
-	@for page in $(MKDOCS_PAGES); do \
+	@comm -23 <(echo '$(DOCSET_PAGE_PATHS)' | tr ' ' '\n') <(echo '$(DOCSET_INDEX_PATHS)' | tr ' ' '\n')
-		case "$$page" in \
-			*/index.md) path=$${page/\/index.md/} ;; \
-			*)          path=$${page/.md/}        ;; \
-		esac; \
-		if [ "x$$page" != "xindex.md" -a "x$$(sqlite3 docSet.dsidx "SELECT COUNT(*) FROM searchIndex WHERE path='$$path/index.html'")" = "x0" ]; then \
-			echo $$page; \
-		fi \
-	done
 
 # list paths in the docset index without a corresponding mkdocs page
 .PHONY: list_removed_paths
 list_removed_paths: docSet.dsidx
-	@for path in $$(sqlite3 docSet.dsidx "SELECT path FROM searchIndex"); do \
+	@comm -13 <(echo '$(DOCSET_PAGE_PATHS)' | tr ' ' '\n') <(echo '$(DOCSET_INDEX_PATHS)' | tr ' ' '\n')
-		page=$${path/\/index.html/.md}; \
-		page_index=$${path/index.html/index.md}; \
-		page_found=0; \
-		for p in $(MKDOCS_PAGES); do \
-			if [ "x$$p" = "x$$page" -o "x$$p" = "x$$page_index" ]; then \
-				page_found=1; \
-			fi \
-		done; \
-		if [ "x$$page_found" = "x0" ]; then \
-			echo $$path; \
-		fi \
-	done
 
 .PHONY: clean
 clean:

docs/docset/README.md

@@ -7,10 +7,11 @@ documentation browsers like [Dash](https://kapeli.com/dash), [Velocity](https://
 The docset can be created with
 
 ```sh
-make nlohmann_json.docset
+make JSON_for_Modern_C++.docset
 ```
 
-The generated folder `nlohmann_json.docset` can then be opened in the documentation browser.
+The generated folder `JSON_for_Modern_C++.docset` can then be opened in the documentation browser. `make all` builds a
+`JSON_for_Modern_C++.tgz` archive instead, and `make install_docset_zeal` installs the docset for Zeal directly.
 
 A recent version is also part of the [Dash user contributions](https://github.com/Kapeli/Dash-User-Contributions/tree/master/docsets/JSON_for_Modern_C%2B%2B).
 

docs/mkdocs/docs/api/basic_json/number_integer_t.md

@@ -51,7 +51,7 @@ range will yield over/underflow when used in a constructor. During deserializati
 will automatically be stored as [`number_unsigned_t`](number_unsigned_t.md) or [`number_float_t`](number_float_t.md).
 
 [RFC 8259](https://tools.ietf.org/html/rfc8259) further states:
-> Note that when such software is used, numbers that are integers and are in the range $[-2^{53}+1, 2^{53}-1]$ are
+> Note that when such software is used, numbers that are integers and are in the range [-2<sup>53</sup>+1, 2<sup>53</sup>-1] are
 > interoperable in the sense that implementations will agree exactly on their numeric values.
 
 As this range is a subrange of the exactly supported range [INT64_MIN, INT64_MAX], this class's integer type is

docs/mkdocs/docs/api/basic_json/number_unsigned_t.md

@@ -52,7 +52,7 @@ when used in a constructor. During deserialization, too large or small integer n
 as [`number_integer_t`](number_integer_t.md) or [`number_float_t`](number_float_t.md).
 
 [RFC 8259](https://tools.ietf.org/html/rfc8259) further states:
-> Note that when such software is used, numbers that are integers and are in the range $[-2^{53}+1, 2^{53}-1]$ are
+> Note that when such software is used, numbers that are integers and are in the range [-2<sup>53</sup>+1, 2<sup>53</sup>-1] are
 > interoperable in the sense that implementations will agree exactly on their numeric values.
 
 As this range is a subrange (when considered in conjunction with the `number_integer_t` type) of the exactly supported

docs/mkdocs/docs/api/basic_json/parse_error.md

@@ -54,7 +54,7 @@ classDiagram
 
 ## Notes
 
-For an input with $n$ bytes, 1 is the index of the first character and $n+1$ is the index of the terminating null byte
+For an input with <i>n</i> bytes, 1 is the index of the first character and <i>n</i>+1 is the index of the terminating null byte
 or the end of file. This also holds true when reading a byte vector for binary formats.
 
 ## Examples

docs/mkdocs/docs/examples/parse__iterator_pair.link

@@ -1 +0,0 @@
-<a target="_blank" href="https://wandbox.org/permlink/hUJYo1HWmfTBLMGn"><b>online</b></a>

docs/mkdocs/docs/examples/parse__pointers.link

@@ -1 +0,0 @@
-<a target="_blank" href="https://wandbox.org/permlink/AWbpa8e1xRV3y4MM"><b>online</b></a>

docs/mkdocs/docs/features/binary_formats/bjdata.md

@@ -61,7 +61,7 @@ The library uses the following mapping from JSON values types to BJData types ac
 
     The following values can **not** be converted to a BJData value:
 
-      - strings with more than 18446744073709551615 bytes, i.e., $2^{64}-1$ bytes (theoretical)
+      - strings with more than 18446744073709551615 bytes, i.e., 2<sup>64</sup>-1 bytes (theoretical)
 
 !!! info "Unused BJData markers"
 

docs/mkdocs/docs/features/types/index.md

@@ -273,7 +273,7 @@ When the default type is used, the maximal unsigned integer number that can be s
 
 [RFC 8259](https://tools.ietf.org/html/rfc8259) further states:
 
-> Note that when such software is used, numbers that are integers and are in the range $[-2^{53}+1, 2^{53}-1]$ are interoperable in the sense that implementations will agree exactly on their numeric values.
+> Note that when such software is used, numbers that are integers and are in the range [-2<sup>53</sup>+1, 2<sup>53</sup>-1] are interoperable in the sense that implementations will agree exactly on their numeric values.
 
 As this range is a subrange of the exactly supported range [`INT64_MIN`, `INT64_MAX`], this class's integer type is interoperable.
 

docs/mkdocs/docs/features/types/number_handling.md

@@ -48,7 +48,7 @@ On number interoperability, the following remarks are made:
     for numeric magnitude and precision than is widely available.
     
     Note that when such software is used, numbers that are integers and
-    are in the range $[-2^{53}+1, 2^{53}-1]$ are interoperable in the
+    are in the range [-2<sup>53</sup>+1, 2<sup>53</sup>-1] are interoperable in the
     sense that implementations will agree exactly on their numeric
     values.
 
@@ -95,9 +95,9 @@ This is the same behavior as the code `#!c double x = 3.141592653589793238462643
 
 !!! success "Interoperability"
 
-    - The library is interoperable with respect to the specification, because its supported range $[-2^{63}, 2^{64}-1]$ is
+    - The library is interoperable with respect to the specification, because its supported range [-2<sup>63</sup>, 2<sup>64</sup>-1] is
-      larger than the described range $[-2^{53}+1, 2^{53}-1]$.
+      larger than the described range [-2<sup>53</sup>+1, 2<sup>53</sup>-1].
-    - All integers outside the range $[-2^{63}, 2^{64}-1]$, as well as floating-point numbers are stored as `double`.
+    - All integers outside the range [-2<sup>63</sup>, 2<sup>64</sup>-1], as well as floating-point numbers are stored as `double`.
       This also concurs with the specification above.
 
 ### Zeros

docs/mkdocs/docs/integration/package_managers.md

@@ -678,11 +678,11 @@ to install the [nlohmann-json](https://ports.macports.org/port/nlohmann-json/) p
     1. Create the following files:
 
         ```cpp title="example.cpp"
-        --8<-- "integration/homebrew/example.cpp"
+        --8<-- "integration/macports/example.cpp"
         ```
 
         ```cmake title="CMakeLists.txt"
-        --8<-- "integration/homebrew/CMakeLists.txt"
+        --8<-- "integration/macports/CMakeLists.txt"
         ```
 
     2. Install the package:

docs/mkdocs/mkdocs.yml

@@ -349,7 +349,6 @@ markdown_extensions:
   - toc:
       permalink: true
   - md_in_html
-  - pymdownx.arithmatex
   - pymdownx.betterem:
       smart_enable: all
   - pymdownx.caret
@@ -441,6 +440,3 @@ plugins:
 
 extra_css:
   - css/custom.css
-
-extra_javascript:
-  - https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-MML-AM_CHTML

docs/mkdocs/scripts/check_structure.py

@@ -79,9 +79,9 @@ def check_structure() -> None:
                     report("whitespace/line_length", f"{file}:{lineno+1} ({current_section})", f"line is too long ({len(line)} vs. 160 chars)")
 
                 # sections in `<!-- NOLINT -->` comments are treated as present
-                if line.startswith("<!-- NOLINT"):
+                nolint_match = re.match(r"<!--\s*NOLINT\s+(.*?)\s*-->", line)
-                    current_section = line.strip("<!-- NOLINT")
+                if nolint_match:
-                    current_section = current_section.strip(" -->")
+                    current_section = nolint_match.group(1)
                     existing_sections.append(current_section)
 
                 # check if sections are correct
@@ -97,7 +97,7 @@ def check_structure() -> None:
                             if len(unexpected):
                                 report("style/numbering", f"{file}:{lineno} ({current_section})", f'unexpected overloads: {", ".join([f"({x})" for x in unexpected])}')
 
-                    current_section = line.strip("## ")
+                    current_section = line[3:]
                     existing_sections.append(current_section)
 
                     if current_section in expected_sections:
@@ -141,7 +141,7 @@ def check_structure() -> None:
                 # check that non-example admonitions have titles
                 untitled_admonition = re.match(r"^(\?\?\?|!!!) ([^ ]+)$", line)
                 if untitled_admonition and untitled_admonition.group(2) != "example":
-                    report("style/admonition_title", f"{file}:{lineno} ({current_section})", f'"{untitled_admonition.group(2)}" admonitions should have a title')
+                    report("style/admonition_title", f"{file}:{lineno+1} ({current_section})", f'"{untitled_admonition.group(2)}" admonitions should have a title')
 
                 previous_line = line