docling/tests/test_backend_csv.py

86 lines
2.5 KiB
Python
Raw Normal View History

import json
import os
from pathlib import Path
from pytest import warns
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult, DoclingDocument
from docling.document_converter import DocumentConverter
feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) * Add DoclingParseV3 backend implementation Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Use docling-core with docling-parse types Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes and test updates Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset tests Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test cases Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test units Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add back DoclingParse v1 backend, pipeline options Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update locks Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: update docling-core to 2.22.0 Update dependency library docling-core to latest release 2.22.0 Fix regression tests and ground truth files Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> * Ground-truth files updated Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update tests, use TextCell.from_ocr property Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Text fixes, new test data Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Rename docling backend to v4 Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Test all backends, fixes Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset all tests to use docling-parse v1 for now Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes for DPv4 backend init, better test coverage Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * test_input_doc use default backend Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
2025-03-18 10:38:19 +01:00
from .test_data_gen_flag import GEN_TEST_DATA
from .verify_utils import verify_document, verify_export
feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) * Add DoclingParseV3 backend implementation Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Use docling-core with docling-parse types Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes and test updates Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset tests Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test cases Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test units Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add back DoclingParse v1 backend, pipeline options Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update locks Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: update docling-core to 2.22.0 Update dependency library docling-core to latest release 2.22.0 Fix regression tests and ground truth files Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> * Ground-truth files updated Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update tests, use TextCell.from_ocr property Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Text fixes, new test data Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Rename docling backend to v4 Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Test all backends, fixes Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset all tests to use docling-parse v1 for now Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes for DPv4 backend init, better test coverage Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * test_input_doc use default backend Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
2025-03-18 10:38:19 +01:00
GENERATE = GEN_TEST_DATA
def get_csv_paths():
# Define the directory you want to search
directory = Path(f"./tests/data/csv/")
# List all CSV files in the directory and its subdirectories
return sorted(directory.rglob("*.csv"))
def get_csv_path(name: str):
# Return the matching CSV file path
return Path(f"./tests/data/csv/{name}.csv")
def get_converter():
converter = DocumentConverter(allowed_formats=[InputFormat.CSV])
return converter
def test_e2e_valid_csv_conversions():
valid_csv_paths = get_csv_paths()
converter = get_converter()
for csv_path in valid_csv_paths:
print(f"converting {csv_path}")
gt_path = csv_path.parent.parent / "groundtruth" / "docling_v2" / csv_path.name
conv_result: ConversionResult = converter.convert(csv_path)
doc: DoclingDocument = conv_result.document
pred_md: str = doc.export_to_markdown()
assert verify_export(pred_md, str(gt_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(gt_path) + ".itxt"
), "export to indented-text"
assert verify_document(
pred_doc=doc,
gtfile=str(gt_path) + ".json",
generate=GENERATE,
), "export to json"
def test_e2e_invalid_csv_conversions():
csv_too_few_columns = get_csv_path("csv-too-few-columns")
csv_too_many_columns = get_csv_path("csv-too-many-columns")
csv_inconsistent_header = get_csv_path("csv-inconsistent-header")
converter = get_converter()
print(f"converting {csv_too_few_columns}")
with warns(UserWarning, match="Inconsistent column lengths"):
converter.convert(csv_too_few_columns)
print(f"converting {csv_too_many_columns}")
with warns(UserWarning, match="Inconsistent column lengths"):
converter.convert(csv_too_many_columns)
print(f"converting {csv_inconsistent_header}")
with warns(UserWarning, match="Inconsistent column lengths"):
converter.convert(csv_inconsistent_header)