feat!: Upgrade to v2.0.0 (#48)

* feat!: Upgrade to v2.0.0

Signed-off-by: Christoph Auer <[email protected]>

* Dummy change

Signed-off-by: Christoph Auer <[email protected]>

* rename old parser as pdf_parser_v1

Signed-off-by: Michele Dolfi <[email protected]>

---------

Signed-off-by: Christoph Auer <[email protected]>
Signed-off-by: Christoph Auer <[email protected]>
Signed-off-by: Michele Dolfi <[email protected]>
Co-authored-by: Michele Dolfi <[email protected]>

Author: cau-git

.github/scripts/build_rhel.sh

@@ -42,7 +42,7 @@ docker build --progress=plain \
     COPY ./dist/*.tar.gz /src/
 
     RUN USE_SYSTEM_DEPS=\$USE_SYSTEM_DEPS pip3.11 install /src/docling_parse*.tar.gz \
-        && python3.11 -c 'from docling_parse.docling_parse import pdf_parser, pdf_parser_v2'
+        && python3.11 -c 'from docling_parse.docling_parse import pdf_parser_v1, pdf_parser_v2'
     
     COPY ./tests /src/tests
 

README.md

@@ -164,7 +164,7 @@ To build the package, simply run (make sure [poetry](https://python-poetry.org/)
 poetry build
 ```
 
-To test the package, run,
+To test the package, run:
 
 ```
 poetry run pytest ./tests -v -s

app/pybind_parse.cpp

@@ -13,7 +13,7 @@
 PYBIND11_MODULE(docling_parse, m) {
 
   // purely for backward compatibility 
-  pybind11::class_<docling::docling_parser_v1>(m, "pdf_parser")
+  pybind11::class_<docling::docling_parser_v1>(m, "pdf_parser_v1")
     .def(pybind11::init())
 
     .def("set_loglevel", &docling::docling_parser_v1::set_loglevel)

docling_parse/eval.py

@@ -5,7 +5,7 @@
 
 from tabulate import tabulate
 
-from docling_parse.docling_parse import pdf_parser
+from docling_parse.docling_parse import pdf_parser_v1
 
 
 def main():
@@ -52,7 +52,7 @@ def main():
 
     # Print the path to the PDF file (or add your processing logic here)
 
-    parser = pdf_parser()
+    parser = pdf_parser_v1()
     parser.set_loglevel(args.log_level)
 
     overview = []

docling_parse/run.py

@@ -4,7 +4,7 @@
 from tabulate import tabulate
 
 import docling_parse
-from docling_parse.docling_parse import pdf_parser
+from docling_parse.docling_parse import pdf_parser_v1
 
 
 def main():
@@ -37,7 +37,7 @@ def main():
 
     # Print the path to the PDF file (or add your processing logic here)
 
-    parser = pdf_parser()
+    parser = pdf_parser_v1()
     parser.set_loglevel(args.log_level)
 
     doc_file = args.pdf  # filename

docling_parse/visualize.py

@@ -5,7 +5,7 @@
 
 from tabulate import tabulate
 
-from docling_parse import pdf_parser, pdf_parser_v2
+from docling_parse import pdf_parser_v1, pdf_parser_v2
 
 try:
     from PIL import Image, ImageDraw
@@ -98,7 +98,7 @@ def visualise_v1(
     log_level: str, pdf_path: str, interactive: str, output_dir: str, page_num: int
 ):
 
-    parser = pdf_parser()
+    parser = pdf_parser_v1()
     parser.set_loglevel_with_label(log_level)
 
     doc_key = "key"

tests/test_parse_v1.py

@@ -38,7 +38,7 @@ def verify_reference_output(true_doc, pred_doc):
 """
 def test_reference_documents_from_filenames():
 
-    parser = docling_parse.pdf_parser()
+    parser = docling_parse.pdf_parser_v1()
 
     pdf_docs = glob.glob("./tests/pdf_docs/tests/*.pdf")
 
@@ -63,7 +63,7 @@ def test_reference_documents_from_filenames():
 """
 def test_reference_documents_from_filenames_page_by_page():
 
-    parser = docling_parse.pdf_parser()
+    parser = docling_parse.pdf_parser_v1()
     
     pdf_docs = glob.glob("./tests/pdf_docs/tests/*.pdf")
 
@@ -90,7 +90,7 @@ def test_reference_documents_from_filenames_page_by_page():
 
 def test_reference_documents_from_filenames_with_keys():
 
-    parser = docling_parse.pdf_parser()
+    parser = docling_parse.pdf_parser_v1()
     #parser.set_loglevel(4)
 
     pdf_docs = glob.glob("./tests/pdf_docs/tests/*.pdf")
@@ -129,7 +129,7 @@ def test_reference_documents_from_filenames_with_keys():
 
 def test_reference_documents_from_filenames_with_keys_page_by_page():
 
-    parser = docling_parse.pdf_parser()
+    parser = docling_parse.pdf_parser_v1()
     #parser.set_loglevel(0)
 
     pdf_docs = glob.glob("./tests/pdf_docs/tests/*.pdf")
@@ -176,7 +176,7 @@ def test_reference_documents_from_filenames_with_keys_page_by_page():
 """
 def test_reference_documents_from_bytesio():
 
-    parser = docling_parse.pdf_parser()
+    parser = docling_parse.pdf_parser_v1()
 
     pdf_docs = glob.glob("./tests/pdf_docs/tests/*.pdf")
 
@@ -209,7 +209,7 @@ def test_reference_documents_from_bytesio():
 """
 def test_reference_documents_from_bytesio_page_by_page():
 
-    parser = docling_parse.pdf_parser()
+    parser = docling_parse.pdf_parser_v1()
     #parser.set_loglevel(1)
     
     pdf_docs = glob.glob("./tests/pdf_docs/tests/*.pdf")
@@ -244,7 +244,7 @@ def test_reference_documents_from_bytesio_page_by_page():
 
 def test_reference_documents_from_bytesio_with_keys():
 
-    parser = docling_parse.pdf_parser()
+    parser = docling_parse.pdf_parser_v1()
 
     pdf_docs = glob.glob("./tests/pdf_docs/tests/*.pdf")
 
@@ -284,7 +284,7 @@ def test_reference_documents_from_bytesio_with_keys():
             assert verify_reference_output(true_doc, pred_doc), "verify_reference_output(true_doc, pred_doc)"                        
 def test_reference_documents_from_bytesio_with_keys_page_by_page():
 
-    parser = docling_parse.pdf_parser()
+    parser = docling_parse.pdf_parser_v1()
     #parser.set_loglevel(4)
 
     pdf_docs = glob.glob("./tests/pdf_docs/tests/*.pdf")