.dockerignore
.gitignore
.gitlab-ci.yml
.pytest.ini
Dockerfile
LICENSE
README.md
compile_grammars.py
create_trie.py
generate_english_trie.py
pyproject.toml
update_trie.py
uv.lock
.github/actions/shared/action.yml
.github/workflows/build-base.yml
.github/workflows/ci.yml
.github/workflows/release.yml
ci/check_version.py
docs/README.md
docs/installation.md
docs/language_data.md
docs/plugins/headings_plugin.md
docs/plugins/hyphen_plugin.md
docs/usage/filter_mode.md
docs/usage/find_mode.md
docs/usage/pegparse_mode.md
docs/usage/regex_mode.md
parseidon_headings_plugin/pyproject.toml
parseidon_headings_plugin/src/parseidon_headings_plugin/remove_headings.py
parseidon_hyphen_plugin/pyproject.toml
parseidon_hyphen_plugin/src/parseidon_hyphen_plugin/dehyphenate.py
src/parseidon/__init__.py
src/parseidon/__main__.py
src/parseidon/hookspecs.py
src/parseidon/main.py
src/parseidon/plugin_manager.py
src/parseidon.egg-info/PKG-INFO
src/parseidon.egg-info/SOURCES.txt
src/parseidon.egg-info/dependency_links.txt
src/parseidon.egg-info/entry_points.txt
src/parseidon.egg-info/requires.txt
src/parseidon.egg-info/top_level.txt
src/parseidon.egg-info/zip-safe
src/parseidon/data/peg_files/peg_grammars.txt
src/parseidon/data/peg_files/peg_grammars_source.yaml
src/parseidon/data/peg_files/individual_pegs/date_peg.txt
src/parseidon/data/peg_files/individual_pegs/doc_id_peg.txt
src/parseidon/data/peg_files/individual_pegs/email_peg.txt
src/parseidon/data/peg_files/individual_pegs/ipv4_peg.txt
src/parseidon/data/peg_files/individual_pegs/ipv6_peg.txt
src/parseidon/data/peg_files/individual_pegs/mac_peg.txt
src/parseidon/data/peg_files/individual_pegs/phonenumber_peg.txt
src/parseidon/data/peg_files/individual_pegs/tech_protocol_peg.txt
src/parseidon/data/peg_files/individual_pegs/unit_peg.txt
src/parseidon/data/peg_files/individual_pegs/url_peg.txt
src/parseidon/data/peg_files/individual_pegs/wifi_peg.txt
src/parseidon/data/regex_files/main_regex.yaml
src/parseidon/data/skip_lists/skip_list1.txt
src/parseidon/data/trie/punctuation.marisa
src/parseidon/data/trie/swedish.marisa
src/parseidon/factory/program_factory.py
src/parseidon/files/excelfile.py
src/parseidon/files/file.py
src/parseidon/files/image_file.py
src/parseidon/files/legacy_excelfile.py
src/parseidon/files/legacy_wordfile.py
src/parseidon/files/pdf_file.py
src/parseidon/files/textfile.py
src/parseidon/files/wordfile.py
src/parseidon/handlers/chain.py
src/parseidon/handlers/content.py
src/parseidon/handlers/content_handler.py
src/parseidon/handlers/conversion_handler.py
src/parseidon/handlers/file_handler.py
src/parseidon/handlers/handler.py
src/parseidon/handlers/image_painter_handler.py
src/parseidon/handlers/match.py
src/parseidon/handlers/output_handler.py
src/parseidon/handlers/matcher_handlers/filter_matcher_handler.py
src/parseidon/handlers/matcher_handlers/matcher_handler.py
src/parseidon/handlers/matcher_handlers/peg_parse_matcher_handler.py
src/parseidon/handlers/matcher_handlers/regex_matcher_handler.py
src/parseidon/helpers/image_helper.py
src/parseidon/helpers/resource_loader.py
src/parseidon/mode/filter_mode.py
src/parseidon/mode/find_mode.py
src/parseidon/mode/mode.py
src/parseidon/mode/pegparse_mode.py
src/parseidon/mode/regex_mode.py
tests/__init__.py
tests/helpers.py
tests/test_arguments.py
tests/test_output.py
tests/test_patterns.py
tests/test_programs.py
tests/handler_tests/test_content_handler.py
tests/handler_tests/test_conversion_handler.py
tests/handler_tests/test_file_handler.py
tests/handler_tests/test_image_painter_handler.py
tests/handler_tests/test_match_handler.py
tests/handler_tests/test_output_handler.py
tests/test_files/bad_peg.md
tests/test_files/bad_peg.txt
tests/test_files/bad_re.yaml
tests/test_files/chart_test.docx
tests/test_files/custom_re.yaml
tests/test_files/custom_test.txt
tests/test_files/doc_test.doc
tests/test_files/docx_tes.docx
tests/test_files/docx_test.docx
tests/test_files/email_test.txt
tests/test_files/filter_text.txt
tests/test_files/footnote_test.docx
tests/test_files/header_footer_test.docx
tests/test_files/hyphenation.pdf
tests/test_files/inline_shape_test.docx
tests/test_files/ip_headings.pdf
tests/test_files/long_doc.doc
tests/test_files/long_docx.docx
tests/test_files/long_pdf.pdf
tests/test_files/md_test.md
tests/test_files/ods_tes.ods
tests/test_files/ods_test.ods
tests/test_files/odt_tes.odt
tests/test_files/odt_test.odt
tests/test_files/pdf_tes.pdf
tests/test_files/pdf_test.pdf
tests/test_files/plaintext_test
tests/test_files/read_doc_test.doc
tests/test_files/slashed.txt
tests/test_files/table_test.docx
tests/test_files/test_all_pat.txt
tests/test_files/test_heading_positions.odt
tests/test_files/test_image.doc
tests/test_files/test_image.docx
tests/test_files/test_image.eps
tests/test_files/test_image.gif
tests/test_files/test_image.jpg
tests/test_files/test_image.pdf
tests/test_files/test_image.png
tests/test_files/test_image.svg
tests/test_files/test_image.tif
tests/test_files/test_image.xls
tests/test_files/test_image.xlsx
tests/test_files/xls_tes.xls
tests/test_files/xls_test.xls
tests/test_files/xlsx_tes.xlsx
tests/test_files/xlsx_test.xlsx
tests/test_files/patterns/dates.csv
tests/test_files/patterns/doc_id.csv
tests/test_files/patterns/email.csv
tests/test_files/patterns/ipv4.csv
tests/test_files/patterns/ipv4_skips.csv
tests/test_files/patterns/ipv6.csv
tests/test_files/patterns/mac.csv
tests/test_files/patterns/phone.csv
tests/test_files/patterns/prot_tech.csv
tests/test_files/patterns/units.csv
tests/test_files/patterns/url.csv
tests/test_files/patterns/wifi.csv
tests/tests_expected_output/chart_exp.txt
tests/tests_expected_output/custom_expected.txt
tests/tests_expected_output/doc_conversion_expected.txt
tests/tests_expected_output/doc_expected.txt
tests/tests_expected_output/docx_expected.txt
tests/tests_expected_output/dummyfile.txt
tests/tests_expected_output/email_expected.txt
tests/tests_expected_output/exec_time_expected.txt
tests/tests_expected_output/exp_all_pat.txt
tests/tests_expected_output/filter_exp.txt
tests/tests_expected_output/footnote_exp.txt
tests/tests_expected_output/hf_exp.txt
tests/tests_expected_output/img_expected.txt
tests/tests_expected_output/img_type_exp.txt
tests/tests_expected_output/inline_exp.txt
tests/tests_expected_output/long_pdf_exp.txt
tests/tests_expected_output/md_expected.txt
tests/tests_expected_output/ods_exp.txt
tests/tests_expected_output/odt_expected.txt
tests/tests_expected_output/pdf_expected.txt
tests/tests_expected_output/plaintext_expected.txt
tests/tests_expected_output/slashed_exp.txt
tests/tests_expected_output/table_exp.txt
tests/tests_expected_output/xls_expected.txt
tests/tests_expected_output/xlsx_expected.txt
tests/tests_expected_output/csv_files/chart_test.docx.csv
tests/tests_expected_output/csv_files/doc_test.doc.csv
tests/tests_expected_output/csv_files/docx_test.docx.csv
tests/tests_expected_output/csv_files/footnote_test.docx.csv
tests/tests_expected_output/csv_files/header_footer_test.docx.csv
tests/tests_expected_output/csv_files/inline_shape_test.docx.csv
tests/tests_expected_output/csv_files/md_test.md.csv
tests/tests_expected_output/csv_files/ods_test.ods.csv
tests/tests_expected_output/csv_files/odt_test.odt.csv
tests/tests_expected_output/csv_files/pdf_test.pdf.csv
tests/tests_expected_output/csv_files/plaintext_test.csv
tests/tests_expected_output/csv_files/table_test.docx.csv
tests/tests_expected_output/csv_files/test_all_pat.txt.csv
tests/tests_expected_output/csv_files/xls_test.xls.csv
tests/tests_expected_output/csv_files/xlsx_test.xlsx.csv
third_party_notices/THIRD_PARTY_NOTICES
third_party_notices/licenses/CC-BY-4.0.txt