commonmarker 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
Potentially problematic release.
This version of commonmarker might be problematic. Click here for more details.
- checksums.yaml +7 -0
- data/Gemfile +8 -0
- data/LICENSE.txt +22 -0
- data/README.md +119 -0
- data/Rakefile +39 -0
- data/bin/commonmarker +41 -0
- data/commonmarker.gemspec +30 -0
- data/ext/commonmarker/cmark/CMakeLists.txt +25 -0
- data/ext/commonmarker/cmark/COPYING +192 -0
- data/ext/commonmarker/cmark/FindAsan.cmake +74 -0
- data/ext/commonmarker/cmark/Makefile +170 -0
- data/ext/commonmarker/cmark/Makefile.nmake +36 -0
- data/ext/commonmarker/cmark/README.md +169 -0
- data/ext/commonmarker/cmark/api_test/CMakeLists.txt +25 -0
- data/ext/commonmarker/cmark/api_test/cplusplus.cpp +15 -0
- data/ext/commonmarker/cmark/api_test/cplusplus.h +17 -0
- data/ext/commonmarker/cmark/api_test/harness.c +102 -0
- data/ext/commonmarker/cmark/api_test/harness.h +42 -0
- data/ext/commonmarker/cmark/api_test/main.c +700 -0
- data/ext/commonmarker/cmark/appveyor.yml +15 -0
- data/ext/commonmarker/cmark/bench/statistics.py +595 -0
- data/ext/commonmarker/cmark/bench/stats.py +19 -0
- data/ext/commonmarker/cmark/benchmarks.md +33 -0
- data/ext/commonmarker/cmark/build/CMakeCache.txt +362 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CMakeCCompiler.cmake +63 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CMakeCXXCompiler.cmake +64 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CMakeDetermineCompilerABI_C.bin +0 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CMakeDetermineCompilerABI_CXX.bin +0 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CMakeSystem.cmake +15 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CompilerIdC/CMakeCCompilerId.c +499 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CompilerIdC/a.out +0 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CompilerIdCXX/CMakeCXXCompilerId.cpp +489 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/3.2.2/CompilerIdCXX/a.out +0 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/CMakeDirectoryInformation.cmake +16 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/CMakeError.log +30 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/CMakeOutput.log +598 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/Makefile.cmake +77 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/Makefile2 +268 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/TargetDirectories.txt +4 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/cmake.check_cache +1 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/feature_tests.bin +0 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/feature_tests.c +34 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/feature_tests.cxx +405 -0
- data/ext/commonmarker/cmark/build/CMakeFiles/progress.marks +1 -0
- data/ext/commonmarker/cmark/build/CTestTestfile.cmake +10 -0
- data/ext/commonmarker/cmark/build/Makefile +237 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/CMakeDirectoryInformation.cmake +16 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/C.includecache +92 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/CXX.includecache +36 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/DependInfo.cmake +29 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/build.make +155 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/cmake_clean.cmake +12 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/cplusplus.cpp.o +0 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/depend.internal +25 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/depend.make +25 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/flags.make +13 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/harness.c.o +0 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/link.txt +1 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/main.c.o +0 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/api_test.dir/progress.make +4 -0
- data/ext/commonmarker/cmark/build/api_test/CMakeFiles/progress.marks +1 -0
- data/ext/commonmarker/cmark/build/api_test/Makefile +277 -0
- data/ext/commonmarker/cmark/build/api_test/api_test +0 -0
- data/ext/commonmarker/cmark/build/api_test/cmake_install.cmake +29 -0
- data/ext/commonmarker/cmark/build/cmake_install.cmake +48 -0
- data/ext/commonmarker/cmark/build/man/CMakeFiles/CMakeDirectoryInformation.cmake +16 -0
- data/ext/commonmarker/cmark/build/man/CMakeFiles/progress.marks +1 -0
- data/ext/commonmarker/cmark/build/man/Makefile +181 -0
- data/ext/commonmarker/cmark/build/man/cmake_install.cmake +37 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/CMakeDirectoryInformation.cmake +16 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/C.includecache +422 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/DependInfo.cmake +39 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/blocks.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/buffer.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/build.make +544 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/cmake_clean.cmake +27 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/cmark.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/cmark_ctype.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/commonmark.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/depend.internal +177 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/depend.make +177 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/flags.make +8 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/houdini_href_e.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/houdini_html_e.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/houdini_html_u.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/html.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/inlines.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/iterator.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/link.txt +1 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/main.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/man.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/node.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/progress.make +19 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/references.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/scanners.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/utf8.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/cmark.dir/xml.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/C.includecache +394 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/DependInfo.cmake +44 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/blocks.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/buffer.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/build.make +522 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/cmake_clean.cmake +27 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/cmark.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/cmark_ctype.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/commonmark.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/depend.internal +169 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/depend.make +169 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/flags.make +8 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/houdini_href_e.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/houdini_html_e.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/houdini_html_u.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/html.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/inlines.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/iterator.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/link.txt +1 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/man.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/node.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/progress.make +18 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/references.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/scanners.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/utf8.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark.dir/xml.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/C.includecache +394 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/DependInfo.cmake +38 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/blocks.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/buffer.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/build.make +519 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/cmake_clean.cmake +26 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/cmake_clean_target.cmake +3 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/cmark.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/cmark_ctype.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/commonmark.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/depend.internal +169 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/depend.make +169 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/flags.make +8 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/houdini_href_e.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/houdini_html_e.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/houdini_html_u.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/html.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/inlines.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/iterator.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/link.txt +2 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/man.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/node.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/progress.make +18 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/references.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/scanners.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/utf8.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/libcmark_static.dir/xml.c.o +0 -0
- data/ext/commonmarker/cmark/build/src/CMakeFiles/progress.marks +1 -0
- data/ext/commonmarker/cmark/build/src/Makefile +814 -0
- data/ext/commonmarker/cmark/build/src/cmake_install.cmake +69 -0
- data/ext/commonmarker/cmark/build/src/cmark +0 -0
- data/ext/commonmarker/cmark/build/src/cmark_export.h +41 -0
- data/ext/commonmarker/cmark/build/src/cmark_version.h +7 -0
- data/ext/commonmarker/cmark/build/src/config.h +23 -0
- data/ext/commonmarker/cmark/build/src/libcmark.0.19.0.dylib +0 -0
- data/ext/commonmarker/cmark/build/src/libcmark.a +0 -0
- data/ext/commonmarker/cmark/build/src/libcmark.dylib +0 -0
- data/ext/commonmarker/cmark/build/src/libcmark.pc +10 -0
- data/ext/commonmarker/cmark/build/testdir/CMakeFiles/CMakeDirectoryInformation.cmake +16 -0
- data/ext/commonmarker/cmark/build/testdir/CMakeFiles/progress.marks +1 -0
- data/ext/commonmarker/cmark/build/testdir/CTestTestfile.cmake +12 -0
- data/ext/commonmarker/cmark/build/testdir/Makefile +181 -0
- data/ext/commonmarker/cmark/build/testdir/cmake_install.cmake +29 -0
- data/ext/commonmarker/cmark/changelog.txt +153 -0
- data/ext/commonmarker/cmark/data/CaseFolding-3.2.0.txt +912 -0
- data/ext/commonmarker/cmark/man/CMakeLists.txt +8 -0
- data/ext/commonmarker/cmark/man/make_man_page.py +131 -0
- data/ext/commonmarker/cmark/man/man1/cmark.1 +54 -0
- data/ext/commonmarker/cmark/man/man3/cmark.3 +583 -0
- data/ext/commonmarker/cmark/nmake.bat +1 -0
- data/ext/commonmarker/cmark/src/CMakeLists.txt +166 -0
- data/ext/commonmarker/cmark/src/bench.h +27 -0
- data/ext/commonmarker/cmark/src/blocks.c +887 -0
- data/ext/commonmarker/cmark/src/buffer.c +381 -0
- data/ext/commonmarker/cmark/src/buffer.h +113 -0
- data/ext/commonmarker/cmark/src/case_fold_switch.inc +2637 -0
- data/ext/commonmarker/cmark/src/chunk.h +110 -0
- data/ext/commonmarker/cmark/src/cmark.c +24 -0
- data/ext/commonmarker/cmark/src/cmark.h +565 -0
- data/ext/commonmarker/cmark/src/cmark_ctype.c +53 -0
- data/ext/commonmarker/cmark/src/cmark_ctype.h +24 -0
- data/ext/commonmarker/cmark/src/cmark_version.h.in +7 -0
- data/ext/commonmarker/cmark/src/commonmark.c +607 -0
- data/ext/commonmarker/cmark/src/config.h.in +23 -0
- data/ext/commonmarker/cmark/src/debug.h +36 -0
- data/ext/commonmarker/cmark/src/houdini.h +52 -0
- data/ext/commonmarker/cmark/src/houdini_href_e.c +107 -0
- data/ext/commonmarker/cmark/src/houdini_html_e.c +81 -0
- data/ext/commonmarker/cmark/src/houdini_html_u.c +116 -0
- data/ext/commonmarker/cmark/src/html.c +322 -0
- data/ext/commonmarker/cmark/src/html_unescape.gperf +2130 -0
- data/ext/commonmarker/cmark/src/html_unescape.h +13375 -0
- data/ext/commonmarker/cmark/src/inlines.c +1147 -0
- data/ext/commonmarker/cmark/src/inlines.h +19 -0
- data/ext/commonmarker/cmark/src/iterator.c +148 -0
- data/ext/commonmarker/cmark/src/iterator.h +25 -0
- data/ext/commonmarker/cmark/src/libcmark.pc.in +10 -0
- data/ext/commonmarker/cmark/src/main.c +191 -0
- data/ext/commonmarker/cmark/src/man.c +287 -0
- data/ext/commonmarker/cmark/src/node.c +873 -0
- data/ext/commonmarker/cmark/src/node.h +82 -0
- data/ext/commonmarker/cmark/src/parser.h +29 -0
- data/ext/commonmarker/cmark/src/references.c +154 -0
- data/ext/commonmarker/cmark/src/references.h +37 -0
- data/ext/commonmarker/cmark/src/scanners.c +15291 -0
- data/ext/commonmarker/cmark/src/scanners.h +41 -0
- data/ext/commonmarker/cmark/src/scanners.re +247 -0
- data/ext/commonmarker/cmark/src/utf8.c +452 -0
- data/ext/commonmarker/cmark/src/utf8.h +22 -0
- data/ext/commonmarker/cmark/src/xml.c +170 -0
- data/ext/commonmarker/cmark/test/CMakeLists.txt +53 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/asterisk +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/attr_generic +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/attr_href +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/attr_xml_lang +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/attr_xmlns +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/backslash +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/backtick +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/colon +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/dashes +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/double_quote +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/entity_builtin +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/entity_decimal +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/entity_external +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/entity_hex +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/equals +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/exclamation +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/greater_than +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/hash +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/hyphen +0 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/indent +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/left_bracket +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/left_paren +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/less_than +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/plus +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/right_bracket +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/right_paren +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/single_quote +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_any +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_brackets +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_cdata +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_dashes +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_empty_dblquotes +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_empty_quotes +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_idrefs +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_parentheses +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/string_pcdata +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_cdata +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_close +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_doctype +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_element +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_entity +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_notation +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_open +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_open_close +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_open_exclamation +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_open_q +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_sq2_close +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/tag_xml_q +1 -0
- data/ext/commonmarker/cmark/test/afl_dictionary/underscore +1 -0
- data/ext/commonmarker/cmark/test/afl_test_cases/test.md +36 -0
- data/ext/commonmarker/cmark/test/cmark.py +40 -0
- data/ext/commonmarker/cmark/test/normalize.py +179 -0
- data/ext/commonmarker/cmark/test/pathological_tests.py +63 -0
- data/ext/commonmarker/cmark/test/roundtrip.sh +2 -0
- data/ext/commonmarker/cmark/test/smart_punct.txt +96 -0
- data/ext/commonmarker/cmark/test/spec.txt +7505 -0
- data/ext/commonmarker/cmark/test/spec_tests.py +139 -0
- data/ext/commonmarker/cmark/toolchain-mingw32.cmake +17 -0
- data/ext/commonmarker/cmark/tools/mkcasefold.pl +22 -0
- data/ext/commonmarker/cmark/wrappers/wrapper.lua +239 -0
- data/ext/commonmarker/cmark/wrappers/wrapper.py +37 -0
- data/ext/commonmarker/cmark/wrappers/wrapper.rb +15 -0
- data/ext/commonmarker/cmark/wrappers/wrapper.rkt +190 -0
- data/ext/commonmarker/commonmarker.c +165 -0
- data/ext/commonmarker/commonmarker.h +11 -0
- data/ext/commonmarker/extconf.rb +18 -0
- data/lib/commonmarker/config.rb +20 -0
- data/lib/commonmarker/version.rb +3 -0
- data/lib/commonmarker.rb +588 -0
- data/test/benchmark.rb +30 -0
- data/test/spec_tests.json +4074 -0
- data/test/test_basics.rb +44 -0
- data/test/test_helper.rb +5 -0
- data/test/test_maliciousness.rb +9 -0
- data/test/test_pathological_inputs.rb +52 -0
- data/test/test_spec.rb +20 -0
- metadata +399 -0
@@ -0,0 +1,887 @@
|
|
1
|
+
#include <stdlib.h>
|
2
|
+
#include <assert.h>
|
3
|
+
#include <stdio.h>
|
4
|
+
|
5
|
+
#include "cmark_ctype.h"
|
6
|
+
#include "config.h"
|
7
|
+
#include "parser.h"
|
8
|
+
#include "cmark.h"
|
9
|
+
#include "node.h"
|
10
|
+
#include "references.h"
|
11
|
+
#include "utf8.h"
|
12
|
+
#include "scanners.h"
|
13
|
+
#include "inlines.h"
|
14
|
+
#include "houdini.h"
|
15
|
+
#include "buffer.h"
|
16
|
+
#include "debug.h"
|
17
|
+
|
18
|
+
#define CODE_INDENT 4
|
19
|
+
#define peek_at(i, n) (i)->data[n]
|
20
|
+
|
21
|
+
static void
|
22
|
+
S_parser_feed(cmark_parser *parser, const unsigned char *buffer, size_t len,
|
23
|
+
bool eof);
|
24
|
+
|
25
|
+
static void
|
26
|
+
S_process_line(cmark_parser *parser, const unsigned char *buffer,
|
27
|
+
size_t bytes);
|
28
|
+
|
29
|
+
static cmark_node* make_block(cmark_node_type tag, int start_line, int start_column)
|
30
|
+
{
|
31
|
+
cmark_node* e;
|
32
|
+
|
33
|
+
e = (cmark_node *)calloc(1, sizeof(*e));
|
34
|
+
if(e != NULL) {
|
35
|
+
e->type = tag;
|
36
|
+
e->open = true;
|
37
|
+
e->start_line = start_line;
|
38
|
+
e->start_column = start_column;
|
39
|
+
e->end_line = start_line;
|
40
|
+
cmark_strbuf_init(&e->string_content, 32);
|
41
|
+
}
|
42
|
+
|
43
|
+
return e;
|
44
|
+
}
|
45
|
+
|
46
|
+
// Create a root document node.
|
47
|
+
static cmark_node* make_document()
|
48
|
+
{
|
49
|
+
cmark_node *e = make_block(NODE_DOCUMENT, 1, 1);
|
50
|
+
return e;
|
51
|
+
}
|
52
|
+
|
53
|
+
cmark_parser *cmark_parser_new(int options)
|
54
|
+
{
|
55
|
+
cmark_parser *parser = (cmark_parser*)malloc(sizeof(cmark_parser));
|
56
|
+
cmark_node *document = make_document();
|
57
|
+
cmark_strbuf *line = (cmark_strbuf*)malloc(sizeof(cmark_strbuf));
|
58
|
+
cmark_strbuf *buf = (cmark_strbuf*)malloc(sizeof(cmark_strbuf));
|
59
|
+
cmark_strbuf_init(line, 256);
|
60
|
+
cmark_strbuf_init(buf, 0);
|
61
|
+
|
62
|
+
parser->refmap = cmark_reference_map_new();
|
63
|
+
parser->root = document;
|
64
|
+
parser->current = document;
|
65
|
+
parser->line_number = 0;
|
66
|
+
parser->curline = line;
|
67
|
+
parser->last_line_length = 0;
|
68
|
+
parser->linebuf = buf;
|
69
|
+
parser->options = options;
|
70
|
+
|
71
|
+
return parser;
|
72
|
+
}
|
73
|
+
|
74
|
+
void cmark_parser_free(cmark_parser *parser)
|
75
|
+
{
|
76
|
+
cmark_strbuf_free(parser->curline);
|
77
|
+
free(parser->curline);
|
78
|
+
cmark_strbuf_free(parser->linebuf);
|
79
|
+
free(parser->linebuf);
|
80
|
+
cmark_reference_map_free(parser->refmap);
|
81
|
+
free(parser);
|
82
|
+
}
|
83
|
+
|
84
|
+
static cmark_node*
|
85
|
+
finalize(cmark_parser *parser, cmark_node* b);
|
86
|
+
|
87
|
+
// Returns true if line has only space characters, else false.
|
88
|
+
static bool is_blank(cmark_strbuf *s, int offset)
|
89
|
+
{
|
90
|
+
while (offset < s->size) {
|
91
|
+
switch (s->ptr[offset]) {
|
92
|
+
case '\n':
|
93
|
+
return true;
|
94
|
+
case ' ':
|
95
|
+
offset++;
|
96
|
+
break;
|
97
|
+
default:
|
98
|
+
return false;
|
99
|
+
}
|
100
|
+
}
|
101
|
+
|
102
|
+
return true;
|
103
|
+
}
|
104
|
+
|
105
|
+
static inline bool can_contain(cmark_node_type parent_type, cmark_node_type child_type)
|
106
|
+
{
|
107
|
+
return ( parent_type == NODE_DOCUMENT ||
|
108
|
+
parent_type == NODE_BLOCK_QUOTE ||
|
109
|
+
parent_type == NODE_ITEM ||
|
110
|
+
(parent_type == NODE_LIST && child_type == NODE_ITEM) );
|
111
|
+
}
|
112
|
+
|
113
|
+
static inline bool accepts_lines(cmark_node_type block_type)
|
114
|
+
{
|
115
|
+
return (block_type == NODE_PARAGRAPH ||
|
116
|
+
block_type == NODE_HEADER ||
|
117
|
+
block_type == NODE_CODE_BLOCK);
|
118
|
+
}
|
119
|
+
|
120
|
+
static void add_line(cmark_node* node, cmark_chunk *ch, int offset)
|
121
|
+
{
|
122
|
+
assert(node->open);
|
123
|
+
cmark_strbuf_put(&node->string_content, ch->data + offset, ch->len - offset);
|
124
|
+
}
|
125
|
+
|
126
|
+
static void remove_trailing_blank_lines(cmark_strbuf *ln)
|
127
|
+
{
|
128
|
+
int i;
|
129
|
+
|
130
|
+
for (i = ln->size - 1; i >= 0; --i) {
|
131
|
+
unsigned char c = ln->ptr[i];
|
132
|
+
|
133
|
+
if (c != ' ' && c != '\t' && c != '\r' && c != '\n')
|
134
|
+
break;
|
135
|
+
}
|
136
|
+
|
137
|
+
if (i < 0) {
|
138
|
+
cmark_strbuf_clear(ln);
|
139
|
+
return;
|
140
|
+
}
|
141
|
+
|
142
|
+
i = cmark_strbuf_strchr(ln, '\n', i);
|
143
|
+
if (i >= 0)
|
144
|
+
cmark_strbuf_truncate(ln, i);
|
145
|
+
}
|
146
|
+
|
147
|
+
// Check to see if a node ends with a blank line, descending
|
148
|
+
// if needed into lists and sublists.
|
149
|
+
static bool ends_with_blank_line(cmark_node* node)
|
150
|
+
{
|
151
|
+
cmark_node *cur = node;
|
152
|
+
while (cur != NULL) {
|
153
|
+
if (cur->last_line_blank) {
|
154
|
+
return true;
|
155
|
+
}
|
156
|
+
if (cur->type == NODE_LIST || cur->type == NODE_ITEM) {
|
157
|
+
cur = cur->last_child;
|
158
|
+
} else {
|
159
|
+
cur = NULL;
|
160
|
+
}
|
161
|
+
}
|
162
|
+
return false;
|
163
|
+
}
|
164
|
+
|
165
|
+
// Break out of all containing lists
|
166
|
+
static int break_out_of_lists(cmark_parser *parser, cmark_node ** bptr)
|
167
|
+
{
|
168
|
+
cmark_node *container = *bptr;
|
169
|
+
cmark_node *b = parser->root;
|
170
|
+
// find first containing NODE_LIST:
|
171
|
+
while (b && b->type != NODE_LIST) {
|
172
|
+
b = b->last_child;
|
173
|
+
}
|
174
|
+
if (b) {
|
175
|
+
while (container && container != b) {
|
176
|
+
container = finalize(parser, container);
|
177
|
+
}
|
178
|
+
finalize(parser, b);
|
179
|
+
*bptr = b->parent;
|
180
|
+
}
|
181
|
+
return 0;
|
182
|
+
}
|
183
|
+
|
184
|
+
|
185
|
+
static cmark_node*
|
186
|
+
finalize(cmark_parser *parser, cmark_node* b)
|
187
|
+
{
|
188
|
+
int firstlinelen;
|
189
|
+
int pos;
|
190
|
+
cmark_node* item;
|
191
|
+
cmark_node* subitem;
|
192
|
+
cmark_node* parent;
|
193
|
+
|
194
|
+
parent = b->parent;
|
195
|
+
|
196
|
+
assert(b->open); // shouldn't call finalize on closed blocks
|
197
|
+
b->open = false;
|
198
|
+
|
199
|
+
if (parser->curline->size == 0) {
|
200
|
+
// end of input - line number has not been incremented
|
201
|
+
b->end_line = parser->line_number;
|
202
|
+
b->end_column = parser->last_line_length;
|
203
|
+
} else if (b->type == NODE_DOCUMENT ||
|
204
|
+
(b->type == NODE_CODE_BLOCK && b->as.code.fenced) ||
|
205
|
+
(b->type == NODE_HEADER && b->as.header.setext)) {
|
206
|
+
b->end_line = parser->line_number;
|
207
|
+
b->end_column = parser->curline->size -
|
208
|
+
(parser->curline->ptr[parser->curline->size - 1] == '\n' ?
|
209
|
+
1 : 0);
|
210
|
+
} else {
|
211
|
+
b->end_line = parser->line_number - 1;
|
212
|
+
b->end_column = parser->last_line_length;
|
213
|
+
}
|
214
|
+
|
215
|
+
switch (b->type) {
|
216
|
+
case NODE_PARAGRAPH:
|
217
|
+
while (cmark_strbuf_at(&b->string_content, 0) == '[' &&
|
218
|
+
(pos = cmark_parse_reference_inline(&b->string_content, parser->refmap))) {
|
219
|
+
|
220
|
+
cmark_strbuf_drop(&b->string_content, pos);
|
221
|
+
}
|
222
|
+
if (is_blank(&b->string_content, 0)) {
|
223
|
+
// remove blank node (former reference def)
|
224
|
+
cmark_node_free(b);
|
225
|
+
}
|
226
|
+
break;
|
227
|
+
|
228
|
+
case NODE_CODE_BLOCK:
|
229
|
+
if (!b->as.code.fenced) { // indented code
|
230
|
+
remove_trailing_blank_lines(&b->string_content);
|
231
|
+
cmark_strbuf_putc(&b->string_content, '\n');
|
232
|
+
} else {
|
233
|
+
|
234
|
+
// first line of contents becomes info
|
235
|
+
firstlinelen = cmark_strbuf_strchr(&b->string_content, '\n', 0);
|
236
|
+
|
237
|
+
cmark_strbuf tmp = GH_BUF_INIT;
|
238
|
+
houdini_unescape_html_f(
|
239
|
+
&tmp,
|
240
|
+
b->string_content.ptr,
|
241
|
+
firstlinelen
|
242
|
+
);
|
243
|
+
cmark_strbuf_trim(&tmp);
|
244
|
+
cmark_strbuf_unescape(&tmp);
|
245
|
+
b->as.code.info = cmark_chunk_buf_detach(&tmp);
|
246
|
+
|
247
|
+
cmark_strbuf_drop(&b->string_content, firstlinelen + 1);
|
248
|
+
}
|
249
|
+
b->as.code.literal = cmark_chunk_buf_detach(&b->string_content);
|
250
|
+
break;
|
251
|
+
|
252
|
+
case NODE_HTML:
|
253
|
+
b->as.literal = cmark_chunk_buf_detach(&b->string_content);
|
254
|
+
break;
|
255
|
+
|
256
|
+
case NODE_LIST: // determine tight/loose status
|
257
|
+
b->as.list.tight = true; // tight by default
|
258
|
+
item = b->first_child;
|
259
|
+
|
260
|
+
while (item) {
|
261
|
+
// check for non-final non-empty list item ending with blank line:
|
262
|
+
if (item->last_line_blank && item->next) {
|
263
|
+
b->as.list.tight = false;
|
264
|
+
break;
|
265
|
+
}
|
266
|
+
// recurse into children of list item, to see if there are
|
267
|
+
// spaces between them:
|
268
|
+
subitem = item->first_child;
|
269
|
+
while (subitem) {
|
270
|
+
if (ends_with_blank_line(subitem) &&
|
271
|
+
(item->next || subitem->next)) {
|
272
|
+
b->as.list.tight = false;
|
273
|
+
break;
|
274
|
+
}
|
275
|
+
subitem = subitem->next;
|
276
|
+
}
|
277
|
+
if (!(b->as.list.tight)) {
|
278
|
+
break;
|
279
|
+
}
|
280
|
+
item = item->next;
|
281
|
+
}
|
282
|
+
|
283
|
+
break;
|
284
|
+
|
285
|
+
default:
|
286
|
+
break;
|
287
|
+
}
|
288
|
+
return parent;
|
289
|
+
}
|
290
|
+
|
291
|
+
// Add a node as child of another. Return pointer to child.
|
292
|
+
static cmark_node* add_child(cmark_parser *parser, cmark_node* parent,
|
293
|
+
cmark_node_type block_type, int start_column)
|
294
|
+
{
|
295
|
+
assert(parent);
|
296
|
+
|
297
|
+
// if 'parent' isn't the kind of node that can accept this child,
|
298
|
+
// then back up til we hit a node that can.
|
299
|
+
while (!can_contain(parent->type, block_type)) {
|
300
|
+
parent = finalize(parser, parent);
|
301
|
+
}
|
302
|
+
|
303
|
+
cmark_node* child = make_block(block_type, parser->line_number, start_column);
|
304
|
+
child->parent = parent;
|
305
|
+
|
306
|
+
if (parent->last_child) {
|
307
|
+
parent->last_child->next = child;
|
308
|
+
child->prev = parent->last_child;
|
309
|
+
} else {
|
310
|
+
parent->first_child = child;
|
311
|
+
child->prev = NULL;
|
312
|
+
}
|
313
|
+
parent->last_child = child;
|
314
|
+
return child;
|
315
|
+
}
|
316
|
+
|
317
|
+
|
318
|
+
// Walk through node and all children, recursively, parsing
|
319
|
+
// string content into inline content where appropriate.
|
320
|
+
static void process_inlines(cmark_node* root, cmark_reference_map *refmap, int options)
|
321
|
+
{
|
322
|
+
cmark_iter *iter = cmark_iter_new(root);
|
323
|
+
cmark_node *cur;
|
324
|
+
cmark_event_type ev_type;
|
325
|
+
|
326
|
+
while ((ev_type = cmark_iter_next(iter)) != CMARK_EVENT_DONE) {
|
327
|
+
cur = cmark_iter_get_node(iter);
|
328
|
+
if (ev_type == CMARK_EVENT_ENTER) {
|
329
|
+
if (cur->type == NODE_PARAGRAPH ||
|
330
|
+
cur->type == NODE_HEADER) {
|
331
|
+
cmark_parse_inlines(cur, refmap, options);
|
332
|
+
}
|
333
|
+
}
|
334
|
+
}
|
335
|
+
|
336
|
+
cmark_iter_free(iter);
|
337
|
+
}
|
338
|
+
|
339
|
+
// Attempts to parse a list item marker (bullet or enumerated).
|
340
|
+
// On success, returns length of the marker, and populates
|
341
|
+
// data with the details. On failure, returns 0.
|
342
|
+
static int parse_list_marker(cmark_chunk *input, int pos, cmark_list **dataptr)
|
343
|
+
{
|
344
|
+
unsigned char c;
|
345
|
+
int startpos;
|
346
|
+
cmark_list *data;
|
347
|
+
|
348
|
+
startpos = pos;
|
349
|
+
c = peek_at(input, pos);
|
350
|
+
|
351
|
+
if (c == '*' || c == '-' || c == '+') {
|
352
|
+
pos++;
|
353
|
+
if (!cmark_isspace(peek_at(input, pos))) {
|
354
|
+
return 0;
|
355
|
+
}
|
356
|
+
data = (cmark_list *)calloc(1, sizeof(*data));
|
357
|
+
if(data == NULL) {
|
358
|
+
return 0;
|
359
|
+
} else {
|
360
|
+
data->marker_offset = 0; // will be adjusted later
|
361
|
+
data->list_type = CMARK_BULLET_LIST;
|
362
|
+
data->bullet_char = c;
|
363
|
+
data->start = 1;
|
364
|
+
data->delimiter = CMARK_PERIOD_DELIM;
|
365
|
+
data->tight = false;
|
366
|
+
}
|
367
|
+
} else if (cmark_isdigit(c)) {
|
368
|
+
int start = 0;
|
369
|
+
|
370
|
+
do {
|
371
|
+
start = (10 * start) + (peek_at(input, pos) - '0');
|
372
|
+
pos++;
|
373
|
+
} while (cmark_isdigit(peek_at(input, pos)));
|
374
|
+
|
375
|
+
c = peek_at(input, pos);
|
376
|
+
if (c == '.' || c == ')') {
|
377
|
+
pos++;
|
378
|
+
if (!cmark_isspace(peek_at(input, pos))) {
|
379
|
+
return 0;
|
380
|
+
}
|
381
|
+
data = (cmark_list *)calloc(1, sizeof(*data));
|
382
|
+
if(data == NULL) {
|
383
|
+
return 0;
|
384
|
+
} else {
|
385
|
+
data->marker_offset = 0; // will be adjusted later
|
386
|
+
data->list_type = CMARK_ORDERED_LIST;
|
387
|
+
data->bullet_char = 0;
|
388
|
+
data->start = start;
|
389
|
+
data->delimiter = (c == '.' ? CMARK_PERIOD_DELIM : CMARK_PAREN_DELIM);
|
390
|
+
data->tight = false;
|
391
|
+
}
|
392
|
+
} else {
|
393
|
+
return 0;
|
394
|
+
}
|
395
|
+
|
396
|
+
} else {
|
397
|
+
return 0;
|
398
|
+
}
|
399
|
+
|
400
|
+
*dataptr = data;
|
401
|
+
return (pos - startpos);
|
402
|
+
}
|
403
|
+
|
404
|
+
// Return 1 if list item belongs in list, else 0.
|
405
|
+
static int lists_match(cmark_list *list_data, cmark_list *item_data)
|
406
|
+
{
|
407
|
+
return (list_data->list_type == item_data->list_type &&
|
408
|
+
list_data->delimiter == item_data->delimiter &&
|
409
|
+
// list_data->marker_offset == item_data.marker_offset &&
|
410
|
+
list_data->bullet_char == item_data->bullet_char);
|
411
|
+
}
|
412
|
+
|
413
|
+
static cmark_node *finalize_document(cmark_parser *parser)
|
414
|
+
{
|
415
|
+
while (parser->current != parser->root) {
|
416
|
+
parser->current = finalize(parser, parser->current);
|
417
|
+
}
|
418
|
+
|
419
|
+
finalize(parser, parser->root);
|
420
|
+
process_inlines(parser->root, parser->refmap, parser->options);
|
421
|
+
|
422
|
+
return parser->root;
|
423
|
+
}
|
424
|
+
|
425
|
+
cmark_node *cmark_parse_file(FILE *f, int options)
|
426
|
+
{
|
427
|
+
unsigned char buffer[4096];
|
428
|
+
cmark_parser *parser = cmark_parser_new(options);
|
429
|
+
size_t bytes;
|
430
|
+
cmark_node *document;
|
431
|
+
|
432
|
+
while ((bytes = fread(buffer, 1, sizeof(buffer), f)) > 0) {
|
433
|
+
bool eof = bytes < sizeof(buffer);
|
434
|
+
S_parser_feed(parser, buffer, bytes, eof);
|
435
|
+
if (eof) {
|
436
|
+
break;
|
437
|
+
}
|
438
|
+
}
|
439
|
+
|
440
|
+
document = cmark_parser_finish(parser);
|
441
|
+
cmark_parser_free(parser);
|
442
|
+
return document;
|
443
|
+
}
|
444
|
+
|
445
|
+
cmark_node *cmark_parse_document(const char *buffer, size_t len, int options)
|
446
|
+
{
|
447
|
+
cmark_parser *parser = cmark_parser_new(options);
|
448
|
+
cmark_node *document;
|
449
|
+
|
450
|
+
S_parser_feed(parser, (const unsigned char *)buffer, len, true);
|
451
|
+
|
452
|
+
document = cmark_parser_finish(parser);
|
453
|
+
cmark_parser_free(parser);
|
454
|
+
return document;
|
455
|
+
}
|
456
|
+
|
457
|
+
void
|
458
|
+
cmark_parser_feed(cmark_parser *parser, const char *buffer, size_t len)
|
459
|
+
{
|
460
|
+
S_parser_feed(parser, (const unsigned char *)buffer, len, false);
|
461
|
+
}
|
462
|
+
|
463
|
+
static void
|
464
|
+
S_parser_feed(cmark_parser *parser, const unsigned char *buffer, size_t len,
|
465
|
+
bool eof)
|
466
|
+
{
|
467
|
+
const unsigned char *end = buffer + len;
|
468
|
+
|
469
|
+
while (buffer < end) {
|
470
|
+
const unsigned char *eol
|
471
|
+
= (const unsigned char *)memchr(buffer, '\n',
|
472
|
+
end - buffer);
|
473
|
+
size_t line_len;
|
474
|
+
|
475
|
+
if (eol) {
|
476
|
+
line_len = eol + 1 - buffer;
|
477
|
+
} else if (eof) {
|
478
|
+
line_len = end - buffer;
|
479
|
+
} else {
|
480
|
+
cmark_strbuf_put(parser->linebuf, buffer, end - buffer);
|
481
|
+
break;
|
482
|
+
}
|
483
|
+
|
484
|
+
if (parser->linebuf->size > 0) {
|
485
|
+
cmark_strbuf_put(parser->linebuf, buffer, line_len);
|
486
|
+
S_process_line(parser, parser->linebuf->ptr,
|
487
|
+
parser->linebuf->size);
|
488
|
+
cmark_strbuf_clear(parser->linebuf);
|
489
|
+
} else {
|
490
|
+
S_process_line(parser, buffer, line_len);
|
491
|
+
}
|
492
|
+
|
493
|
+
buffer += line_len;
|
494
|
+
}
|
495
|
+
}
|
496
|
+
|
497
|
+
static void chop_trailing_hashtags(cmark_chunk *ch)
|
498
|
+
{
|
499
|
+
int n, orig_n;
|
500
|
+
|
501
|
+
cmark_chunk_rtrim(ch);
|
502
|
+
orig_n = n = ch->len - 1;
|
503
|
+
|
504
|
+
// if string ends in space followed by #s, remove these:
|
505
|
+
while (n >= 0 && peek_at(ch, n) == '#')
|
506
|
+
n--;
|
507
|
+
|
508
|
+
// Check for a be a space before the final #s:
|
509
|
+
if (n != orig_n && n >= 0 && peek_at(ch, n) == ' ') {
|
510
|
+
ch->len = n;
|
511
|
+
cmark_chunk_rtrim(ch);
|
512
|
+
}
|
513
|
+
}
|
514
|
+
|
515
|
+
static void
|
516
|
+
S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes)
|
517
|
+
{
|
518
|
+
cmark_node* last_matched_container;
|
519
|
+
int offset = 0;
|
520
|
+
int matched = 0;
|
521
|
+
int lev = 0;
|
522
|
+
int i;
|
523
|
+
cmark_list *data = NULL;
|
524
|
+
bool all_matched = true;
|
525
|
+
cmark_node* container;
|
526
|
+
bool blank = false;
|
527
|
+
int first_nonspace;
|
528
|
+
int indent;
|
529
|
+
cmark_chunk input;
|
530
|
+
bool maybe_lazy;
|
531
|
+
|
532
|
+
utf8proc_detab(parser->curline, buffer, bytes);
|
533
|
+
|
534
|
+
// Add a newline to the end if not present:
|
535
|
+
// TODO this breaks abstraction:
|
536
|
+
if (parser->curline->ptr[parser->curline->size - 1] != '\n') {
|
537
|
+
cmark_strbuf_putc(parser->curline, '\n');
|
538
|
+
}
|
539
|
+
input.data = parser->curline->ptr;
|
540
|
+
input.len = parser->curline->size;
|
541
|
+
|
542
|
+
// container starts at the document root.
|
543
|
+
container = parser->root;
|
544
|
+
|
545
|
+
parser->line_number++;
|
546
|
+
|
547
|
+
// for each containing node, try to parse the associated line start.
|
548
|
+
// bail out on failure: container will point to the last matching node.
|
549
|
+
|
550
|
+
while (container->last_child && container->last_child->open) {
|
551
|
+
container = container->last_child;
|
552
|
+
|
553
|
+
first_nonspace = offset;
|
554
|
+
while (peek_at(&input, first_nonspace) == ' ') {
|
555
|
+
first_nonspace++;
|
556
|
+
}
|
557
|
+
|
558
|
+
indent = first_nonspace - offset;
|
559
|
+
blank = peek_at(&input, first_nonspace) == '\n';
|
560
|
+
|
561
|
+
if (container->type == NODE_BLOCK_QUOTE) {
|
562
|
+
matched = indent <= 3 && peek_at(&input, first_nonspace) == '>';
|
563
|
+
if (matched) {
|
564
|
+
offset = first_nonspace + 1;
|
565
|
+
if (peek_at(&input, offset) == ' ')
|
566
|
+
offset++;
|
567
|
+
} else {
|
568
|
+
all_matched = false;
|
569
|
+
}
|
570
|
+
|
571
|
+
} else if (container->type == NODE_ITEM) {
|
572
|
+
|
573
|
+
if (indent >= container->as.list.marker_offset +
|
574
|
+
container->as.list.padding) {
|
575
|
+
offset += container->as.list.marker_offset +
|
576
|
+
container->as.list.padding;
|
577
|
+
} else if (blank) {
|
578
|
+
offset = first_nonspace;
|
579
|
+
} else {
|
580
|
+
all_matched = false;
|
581
|
+
}
|
582
|
+
|
583
|
+
} else if (container->type == NODE_CODE_BLOCK) {
|
584
|
+
|
585
|
+
if (!container->as.code.fenced) { // indented
|
586
|
+
if (indent >= CODE_INDENT) {
|
587
|
+
offset += CODE_INDENT;
|
588
|
+
} else if (blank) {
|
589
|
+
offset = first_nonspace;
|
590
|
+
} else {
|
591
|
+
all_matched = false;
|
592
|
+
}
|
593
|
+
} else { // fenced
|
594
|
+
matched = 0;
|
595
|
+
if (indent <= 3 &&
|
596
|
+
(peek_at(&input, first_nonspace) ==
|
597
|
+
container->as.code.fence_char)) {
|
598
|
+
matched = scan_close_code_fence(&input,
|
599
|
+
first_nonspace);
|
600
|
+
}
|
601
|
+
if (matched >= container->as.code.fence_length) {
|
602
|
+
// closing fence - and since we're at
|
603
|
+
// the end of a line, we can return:
|
604
|
+
all_matched = false;
|
605
|
+
offset += matched;
|
606
|
+
parser->current = finalize(parser, container);
|
607
|
+
goto finished;
|
608
|
+
} else {
|
609
|
+
// skip opt. spaces of fence offset
|
610
|
+
i = container->as.code.fence_offset;
|
611
|
+
while (i > 0 &&
|
612
|
+
peek_at(&input, offset) == ' ') {
|
613
|
+
offset++;
|
614
|
+
i--;
|
615
|
+
}
|
616
|
+
}
|
617
|
+
}
|
618
|
+
} else if (container->type == NODE_HEADER) {
|
619
|
+
|
620
|
+
// a header can never contain more than one line
|
621
|
+
all_matched = false;
|
622
|
+
|
623
|
+
} else if (container->type == NODE_HTML) {
|
624
|
+
|
625
|
+
if (blank) {
|
626
|
+
all_matched = false;
|
627
|
+
}
|
628
|
+
|
629
|
+
} else if (container->type == NODE_PARAGRAPH) {
|
630
|
+
|
631
|
+
if (blank) {
|
632
|
+
all_matched = false;
|
633
|
+
}
|
634
|
+
|
635
|
+
}
|
636
|
+
|
637
|
+
if (!all_matched) {
|
638
|
+
container = container->parent; // back up to last matching node
|
639
|
+
break;
|
640
|
+
}
|
641
|
+
}
|
642
|
+
|
643
|
+
last_matched_container = container;
|
644
|
+
|
645
|
+
// check to see if we've hit 2nd blank line, break out of list:
|
646
|
+
if (blank && container->last_line_blank) {
|
647
|
+
break_out_of_lists(parser, &container);
|
648
|
+
}
|
649
|
+
|
650
|
+
maybe_lazy = parser->current->type == NODE_PARAGRAPH;
|
651
|
+
// try new container starts:
|
652
|
+
while (container->type != NODE_CODE_BLOCK &&
|
653
|
+
container->type != NODE_HTML) {
|
654
|
+
|
655
|
+
first_nonspace = offset;
|
656
|
+
while (peek_at(&input, first_nonspace) == ' ')
|
657
|
+
first_nonspace++;
|
658
|
+
|
659
|
+
indent = first_nonspace - offset;
|
660
|
+
blank = peek_at(&input, first_nonspace) == '\n';
|
661
|
+
|
662
|
+
if (indent >= CODE_INDENT) {
|
663
|
+
if (!maybe_lazy && !blank) {
|
664
|
+
offset += CODE_INDENT;
|
665
|
+
container = add_child(parser, container, NODE_CODE_BLOCK, offset + 1);
|
666
|
+
container->as.code.fenced = false;
|
667
|
+
container->as.code.fence_char = 0;
|
668
|
+
container->as.code.fence_length = 0;
|
669
|
+
container->as.code.fence_offset = 0;
|
670
|
+
container->as.code.info = cmark_chunk_literal("");
|
671
|
+
} else { // indent > 4 in lazy line
|
672
|
+
break;
|
673
|
+
}
|
674
|
+
|
675
|
+
} else if (peek_at(&input, first_nonspace) == '>') {
|
676
|
+
|
677
|
+
offset = first_nonspace + 1;
|
678
|
+
// optional following character
|
679
|
+
if (peek_at(&input, offset) == ' ')
|
680
|
+
offset++;
|
681
|
+
container = add_child(parser, container, NODE_BLOCK_QUOTE, offset + 1);
|
682
|
+
|
683
|
+
} else if ((matched = scan_atx_header_start(&input, first_nonspace))) {
|
684
|
+
|
685
|
+
offset = first_nonspace + matched;
|
686
|
+
container = add_child(parser, container, NODE_HEADER, offset + 1);
|
687
|
+
|
688
|
+
int hashpos = cmark_chunk_strchr(&input, '#', first_nonspace);
|
689
|
+
int level = 0;
|
690
|
+
|
691
|
+
while (peek_at(&input, hashpos) == '#') {
|
692
|
+
level++;
|
693
|
+
hashpos++;
|
694
|
+
}
|
695
|
+
container->as.header.level = level;
|
696
|
+
container->as.header.setext = false;
|
697
|
+
|
698
|
+
} else if ((matched = scan_open_code_fence(&input, first_nonspace))) {
|
699
|
+
|
700
|
+
container = add_child(parser, container, NODE_CODE_BLOCK, first_nonspace + 1);
|
701
|
+
container->as.code.fenced = true;
|
702
|
+
container->as.code.fence_char = peek_at(&input, first_nonspace);
|
703
|
+
container->as.code.fence_length = matched;
|
704
|
+
container->as.code.fence_offset = first_nonspace - offset;
|
705
|
+
container->as.code.info = cmark_chunk_literal("");
|
706
|
+
offset = first_nonspace + matched;
|
707
|
+
|
708
|
+
} else if ((matched = scan_html_block_tag(&input, first_nonspace))) {
|
709
|
+
|
710
|
+
container = add_child(parser, container, NODE_HTML, first_nonspace + 1);
|
711
|
+
// note, we don't adjust offset because the tag is part of the text
|
712
|
+
|
713
|
+
} else if (container->type == NODE_PARAGRAPH &&
|
714
|
+
(lev = scan_setext_header_line(&input, first_nonspace)) &&
|
715
|
+
// check that there is only one line in the paragraph:
|
716
|
+
cmark_strbuf_strrchr(&container->string_content, '\n',
|
717
|
+
cmark_strbuf_len(&container->string_content) - 2) < 0) {
|
718
|
+
|
719
|
+
container->type = NODE_HEADER;
|
720
|
+
container->as.header.level = lev;
|
721
|
+
container->as.header.setext = true;
|
722
|
+
offset = input.len - 1;
|
723
|
+
|
724
|
+
} else if (!(container->type == NODE_PARAGRAPH && !all_matched) &&
|
725
|
+
(matched = scan_hrule(&input, first_nonspace))) {
|
726
|
+
|
727
|
+
// it's only now that we know the line is not part of a setext header:
|
728
|
+
container = add_child(parser, container, NODE_HRULE, first_nonspace + 1);
|
729
|
+
container = finalize(parser, container);
|
730
|
+
offset = input.len - 1;
|
731
|
+
|
732
|
+
} else if ((matched = parse_list_marker(&input, first_nonspace, &data))) {
|
733
|
+
|
734
|
+
// compute padding:
|
735
|
+
offset = first_nonspace + matched;
|
736
|
+
i = 0;
|
737
|
+
while (i <= 5 && peek_at(&input, offset + i) == ' ') {
|
738
|
+
i++;
|
739
|
+
}
|
740
|
+
// i = number of spaces after marker, up to 5
|
741
|
+
if (i >= 5 || i < 1 || peek_at(&input, offset) == '\n') {
|
742
|
+
data->padding = matched + 1;
|
743
|
+
if (i > 0) {
|
744
|
+
offset += 1;
|
745
|
+
}
|
746
|
+
} else {
|
747
|
+
data->padding = matched + i;
|
748
|
+
offset += i;
|
749
|
+
}
|
750
|
+
|
751
|
+
// check container; if it's a list, see if this list item
|
752
|
+
// can continue the list; otherwise, create a list container.
|
753
|
+
|
754
|
+
data->marker_offset = indent;
|
755
|
+
|
756
|
+
if (container->type != NODE_LIST ||
|
757
|
+
!lists_match(&container->as.list, data)) {
|
758
|
+
container = add_child(parser, container, NODE_LIST,
|
759
|
+
first_nonspace + 1);
|
760
|
+
|
761
|
+
memcpy(&container->as.list, data, sizeof(*data));
|
762
|
+
}
|
763
|
+
|
764
|
+
// add the list item
|
765
|
+
container = add_child(parser, container, NODE_ITEM,
|
766
|
+
first_nonspace + 1);
|
767
|
+
/* TODO: static */
|
768
|
+
memcpy(&container->as.list, data, sizeof(*data));
|
769
|
+
free(data);
|
770
|
+
} else {
|
771
|
+
break;
|
772
|
+
}
|
773
|
+
|
774
|
+
if (accepts_lines(container->type)) {
|
775
|
+
// if it's a line container, it can't contain other containers
|
776
|
+
break;
|
777
|
+
}
|
778
|
+
maybe_lazy = false;
|
779
|
+
}
|
780
|
+
|
781
|
+
// what remains at offset is a text line. add the text to the
|
782
|
+
// appropriate container.
|
783
|
+
|
784
|
+
first_nonspace = offset;
|
785
|
+
while (peek_at(&input, first_nonspace) == ' ')
|
786
|
+
first_nonspace++;
|
787
|
+
|
788
|
+
indent = first_nonspace - offset;
|
789
|
+
blank = peek_at(&input, first_nonspace) == '\n';
|
790
|
+
|
791
|
+
if (blank && container->last_child) {
|
792
|
+
container->last_child->last_line_blank = true;
|
793
|
+
}
|
794
|
+
|
795
|
+
// block quote lines are never blank as they start with >
|
796
|
+
// and we don't count blanks in fenced code for purposes of tight/loose
|
797
|
+
// lists or breaking out of lists. we also don't set last_line_blank
|
798
|
+
// on an empty list item.
|
799
|
+
container->last_line_blank = (blank &&
|
800
|
+
container->type != NODE_BLOCK_QUOTE &&
|
801
|
+
container->type != NODE_HEADER &&
|
802
|
+
!(container->type == NODE_CODE_BLOCK &&
|
803
|
+
container->as.code.fenced) &&
|
804
|
+
!(container->type == NODE_ITEM &&
|
805
|
+
container->first_child == NULL &&
|
806
|
+
container->start_line == parser->line_number));
|
807
|
+
|
808
|
+
cmark_node *cont = container;
|
809
|
+
while (cont->parent) {
|
810
|
+
cont->parent->last_line_blank = false;
|
811
|
+
cont = cont->parent;
|
812
|
+
}
|
813
|
+
|
814
|
+
if (parser->current != last_matched_container &&
|
815
|
+
container == last_matched_container &&
|
816
|
+
!blank &&
|
817
|
+
parser->current->type == NODE_PARAGRAPH &&
|
818
|
+
cmark_strbuf_len(&parser->current->string_content) > 0) {
|
819
|
+
|
820
|
+
add_line(parser->current, &input, offset);
|
821
|
+
|
822
|
+
} else { // not a lazy continuation
|
823
|
+
|
824
|
+
// finalize any blocks that were not matched and set cur to container:
|
825
|
+
while (parser->current != last_matched_container) {
|
826
|
+
parser->current = finalize(parser, parser->current);
|
827
|
+
assert(parser->current != NULL);
|
828
|
+
}
|
829
|
+
|
830
|
+
if (container->type == NODE_CODE_BLOCK ||
|
831
|
+
container->type == NODE_HTML) {
|
832
|
+
|
833
|
+
add_line(container, &input, offset);
|
834
|
+
|
835
|
+
} else if (blank) {
|
836
|
+
|
837
|
+
// ??? do nothing
|
838
|
+
|
839
|
+
} else if (accepts_lines(container->type)) {
|
840
|
+
|
841
|
+
if (container->type == NODE_HEADER &&
|
842
|
+
container->as.header.setext == false) {
|
843
|
+
chop_trailing_hashtags(&input);
|
844
|
+
}
|
845
|
+
add_line(container, &input, first_nonspace);
|
846
|
+
|
847
|
+
} else {
|
848
|
+
// create paragraph container for line
|
849
|
+
container = add_child(parser, container, NODE_PARAGRAPH, first_nonspace + 1);
|
850
|
+
add_line(container, &input, first_nonspace);
|
851
|
+
|
852
|
+
}
|
853
|
+
|
854
|
+
parser->current = container;
|
855
|
+
}
|
856
|
+
finished:
|
857
|
+
parser->last_line_length = parser->curline->size -
|
858
|
+
(parser->curline->ptr[parser->curline->size - 1] == '\n' ?
|
859
|
+
1 : 0);
|
860
|
+
;
|
861
|
+
cmark_strbuf_clear(parser->curline);
|
862
|
+
|
863
|
+
}
|
864
|
+
|
865
|
+
cmark_node *cmark_parser_finish(cmark_parser *parser)
|
866
|
+
{
|
867
|
+
if (parser->linebuf->size) {
|
868
|
+
S_process_line(parser, parser->linebuf->ptr,
|
869
|
+
parser->linebuf->size);
|
870
|
+
cmark_strbuf_clear(parser->linebuf);
|
871
|
+
}
|
872
|
+
|
873
|
+
finalize_document(parser);
|
874
|
+
|
875
|
+
if (parser->options & CMARK_OPT_NORMALIZE) {
|
876
|
+
cmark_consolidate_text_nodes(parser->root);
|
877
|
+
}
|
878
|
+
|
879
|
+
cmark_strbuf_free(parser->curline);
|
880
|
+
|
881
|
+
#if CMARK_DEBUG_NODES
|
882
|
+
if (cmark_node_check(parser->root, stderr)) {
|
883
|
+
abort();
|
884
|
+
}
|
885
|
+
#endif
|
886
|
+
return parser->root;
|
887
|
+
}
|