From 409bc6c5e468cfaadc6ae74bae2bf27751e36dd6 Mon Sep 17 00:00:00 2001 From: EmmaBeni Date: Mon, 3 Aug 2026 00:41:15 -0300 Subject: [PATCH] Everything ran. Cahnges applied to paths in README.md and GETTING_STARTED.md, they wouldn't work --- .idea/.gitignore | 5 +++++ .idea/inspectionProfiles/profiles_settings.xml | 6 ++++++ .idea/misc.xml | 7 +++++++ .idea/modules.xml | 8 ++++++++ .idea/structure.iml | 15 +++++++++++++++ .idea/vcs.xml | 6 ++++++ README.md | 4 ++-- docs/GETTING_STARTED.md | 6 +++--- 8 files changed, 52 insertions(+), 5 deletions(-) create mode 100644 .idea/.gitignore create mode 100644 .idea/inspectionProfiles/profiles_settings.xml create mode 100644 .idea/misc.xml create mode 100644 .idea/modules.xml create mode 100644 .idea/structure.iml create mode 100644 .idea/vcs.xml diff --git a/.idea/.gitignore b/.idea/.gitignore new file mode 100644 index 0000000..b58b603 --- /dev/null +++ b/.idea/.gitignore @@ -0,0 +1,5 @@ +# Default ignored files +/shelf/ +/workspace.xml +# Editor-based HTTP Client requests +/httpRequests/ diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml new file mode 100644 index 0000000..105ce2d --- /dev/null +++ b/.idea/inspectionProfiles/profiles_settings.xml @@ -0,0 +1,6 @@ + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml new file mode 100644 index 0000000..1d3ce46 --- /dev/null +++ b/.idea/misc.xml @@ -0,0 +1,7 @@ + + + + + + \ No newline at end of file diff --git a/.idea/modules.xml b/.idea/modules.xml new file mode 100644 index 0000000..70148b8 --- /dev/null +++ b/.idea/modules.xml @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/structure.iml b/.idea/structure.iml new file mode 100644 index 0000000..c8c430b --- /dev/null +++ b/.idea/structure.iml @@ -0,0 +1,15 @@ + + + + + + + + + + + + \ No newline at end of file diff --git a/.idea/vcs.xml b/.idea/vcs.xml new file mode 100644 index 0000000..35eb1dd --- /dev/null +++ b/.idea/vcs.xml @@ -0,0 +1,6 @@ + + + + + + \ No newline at end of file diff --git a/README.md b/README.md index ff1af15..e05953b 100644 --- a/README.md +++ b/README.md @@ -17,8 +17,8 @@ Docling HTML is a starting point, not the final semantic document. Expect manual ```bash pip install -e ".[docling,dev]" -python -m structure.convert.docling.cli pilot/examples/iari_2024.pdf --document-id iari-2024 -python -m structure.validate.html.cli pilot/examples/html/iari_2024.html +python -m structure.convert.docling.cli pilot/examples/iari-2024/annual_report.pdf --document-id iari-2024 +python -m structure.validate.html.cli pilot/examples/iari-2024/annual_report.raw.html pytest test/ -v ``` diff --git a/docs/GETTING_STARTED.md b/docs/GETTING_STARTED.md index 7c296ed..c270587 100644 --- a/docs/GETTING_STARTED.md +++ b/docs/GETTING_STARTED.md @@ -31,7 +31,7 @@ Docling pulls PyTorch and layout models on first run; allow time and disk space ```bash python -m structure.convert.docling.cli \ - pilot/examples/iari_2024.pdf \ + pilot/examples/iari-2024/annual_report.pdf \ --document-id iari-2024 ``` @@ -43,12 +43,12 @@ ingest/convert/iari-2024/ └── manifest.json ``` -Open `document.html` in a browser to review. Compare with the committed reference at `pilot/examples/html/iari_2024.html` if useful. +Open `document.html` in a browser to review. Compare with the committed reference at `pilot/examples/iari-2024/annual_report.raw.html` if useful. Validate HTML (no PDF required): ```bash -python -m structure.validate.html.cli pilot/examples/html/iari_2024.html --fail-on-issues +python -m structure.validate.html.cli pilot/examples/iari-2024/annual_report.raw.html --fail-on-issues ``` See [`docs/validation.md`](validation.md) for check codes and suggested future rules.