mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-30 14:04:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

reformatted the text

Browse Source 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar 2024-10-29 06:02:49 +01:00
parent 7cb7da7ce9
commit 6163409305
3 changed files with 67 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
tests/test_backend_html.py
View File

@ -1,15 +1,18 @@
import os
import json
import os
from pathlib import Path
from docling.backend.html_backend import HTMLDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import InputDocument, SectionHeaderItem
from docling.datamodel.document import ConversionResult
from docling.datamodel.document import (
ConversionResult,
InputDocument,
SectionHeaderItem,
)
from docling.document_converter import DocumentConverter
GENERATE=False
GENERATE = False
def test_heading_levels():
in_path = Path("tests/data/html/wiki_duck.html")
@ -35,6 +38,7 @@ def test_heading_levels():
assert item.level == 3
assert found_lvl_2 and found_lvl_3
def get_html_paths():
# Define the directory you want to search
@ -44,15 +48,15 @@ def get_html_paths():
html_files = sorted(directory.rglob("*.html"))
return html_files
def get_converter():
converter = DocumentConverter(
allowed_formats = [InputFormat.HTML]
)
converter = DocumentConverter(allowed_formats=[InputFormat.HTML])
return converter
def verify_export(pred_text:str, gtfile:str):
def verify_export(pred_text: str, gtfile: str):
if not os.path.exists(gtfile) or GENERATE:
with open(gtfile, "w") as fw:
@ -64,8 +68,9 @@ def verify_export(pred_text:str, gtfile:str):
with open(gtfile, "r") as fr:
true_text = fr.read()
assert pred_text==true_text, "pred_itxt==true_itxt"
return pred_text==true_text
assert pred_text == true_text, "pred_itxt==true_itxt"
return pred_text == true_text
def test_e2e_html_conversions():
@ -73,19 +78,21 @@ def test_e2e_html_conversions():
converter = get_converter()
for html_path in html_paths:
#print(f"converting {html_path}")
# print(f"converting {html_path}")
conv_result: ConversionResult = converter.convert(html_path)
doc: DoclingDocument = conv_result.document
pred_md:str = doc.export_to_markdown()
assert verify_export(pred_md, str(html_path)+".md"), "export to md"
pred_itxt:str = doc._export_to_indented_text(max_text_len=70, explicit_tables=False)
assert verify_export(pred_itxt, str(html_path)+".itxt"), "export to indented-text"
pred_json:str = json.dumps(doc.export_to_dict(), indent=2)
assert verify_export(pred_json, str(html_path)+".json"), "export to json"
pred_md: str = doc.export_to_markdown()
assert verify_export(pred_md, str(html_path) + ".md"), "export to md"
pred_itxt: str = doc._export_to_indented_text(
max_text_len=70, explicit_tables=False
)
assert verify_export(
pred_itxt, str(html_path) + ".itxt"
), "export to indented-text"
pred_json: str = json.dumps(doc.export_to_dict(), indent=2)
assert verify_export(pred_json, str(html_path) + ".json"), "export to json"

44
tests/test_backend_msword.py
View File

@ -1,15 +1,18 @@
import os
import json
import os
from pathlib import Path
from docling.backend.msword_backend import MsWordDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import InputDocument, SectionHeaderItem
from docling.datamodel.document import ConversionResult
from docling.datamodel.document import (
ConversionResult,
InputDocument,
SectionHeaderItem,
)
from docling.document_converter import DocumentConverter
GENERATE=False
GENERATE = False
def test_heading_levels():
in_path = Path("tests/data/docx/word_sample.docx")
@ -45,15 +48,15 @@ def get_docx_paths():
pdf_files = sorted(directory.rglob("*.docx"))
return pdf_files
def get_converter():
converter = DocumentConverter(
allowed_formats = [InputFormat.DOCX]
)
converter = DocumentConverter(allowed_formats=[InputFormat.DOCX])
return converter
def verify_export(pred_text:str, gtfile:str):
def verify_export(pred_text: str, gtfile: str):
if not os.path.exists(gtfile) or GENERATE:
with open(gtfile, "w") as fw:
@ -65,8 +68,8 @@ def verify_export(pred_text:str, gtfile:str):
with open(gtfile, "r") as fr:
true_text = fr.read()
assert pred_text==true_text, "pred_itxt==true_itxt"
return pred_text==true_text
assert pred_text == true_text, "pred_itxt==true_itxt"
return pred_text == true_text
def test_e2e_docx_conversions():
@ -75,18 +78,21 @@ def test_e2e_docx_conversions():
converter = get_converter()
for docx_path in docx_paths:
#print(f"converting {docx_path}")
# print(f"converting {docx_path}")
conv_result: ConversionResult = converter.convert(docx_path)
doc: DoclingDocument = conv_result.document
pred_md:str = doc.export_to_markdown()
assert verify_export(pred_md, str(docx_path)+".md"), "export to md"
pred_md: str = doc.export_to_markdown()
assert verify_export(pred_md, str(docx_path) + ".md"), "export to md"
pred_itxt:str = doc._export_to_indented_text(max_text_len=70, explicit_tables=False)
assert verify_export(pred_itxt, str(docx_path)+".itxt"), "export to indented-text"
pred_json:str = json.dumps(doc.export_to_dict(), indent=2)
assert verify_export(pred_json, str(docx_path)+".json"), "export to json"
pred_itxt: str = doc._export_to_indented_text(
max_text_len=70, explicit_tables=False
)
assert verify_export(
pred_itxt, str(docx_path) + ".itxt"
), "export to indented-text"
pred_json: str = json.dumps(doc.export_to_dict(), indent=2)
assert verify_export(pred_json, str(docx_path) + ".json"), "export to json"