mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

test: avoid testing exact JSON (#1027)

Browse Source 
* test: avoid testing exact JSON

Avoid testing exact JSON output in html and xml backends.
Reuse the JSON verify helper function among backend test files.
Improve type annotations in html backend.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* Update tests/test_backend_patent_uspto.py

Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

---------

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-02-20 16:20:07 +01:00
committed by GitHub
parent 6796f0a132
commit 1ac010354f
8 changed files with 54 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
docling/backend/html_backend.py
View File

@@ -5,9 +5,11 @@ from typing import Optional, Union, cast
from bs4 import BeautifulSoup, NavigableString, PageElement, Tag
from docling_core.types.doc import (
DocItem,
DocItemLabel,
DoclingDocument,
DocumentOrigin,
GroupItem,
GroupLabel,
TableCell,
TableData,
@@ -32,10 +34,9 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
# Initialise the parents for the hierarchy
self.max_levels = 10
self.level = 0
self.parents = {} # type: ignore
self.parents: dict[int, Optional[Union[DocItem, GroupItem]]] = {}
for i in range(0, self.max_levels):
self.parents[i] = None
self.labels = {} # type: ignore
try:
if isinstance(self.path_or_stream, BytesIO):
@@ -111,11 +112,6 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
return
def analyze_tag(self, tag: Tag, doc: DoclingDocument) -> None:
if tag.name in self.labels:
self.labels[tag.name] += 1
else:
self.labels[tag.name] = 1
if tag.name in ["h1", "h2", "h3", "h4", "h5", "h6"]:
self.handle_header(tag, doc)
elif tag.name in ["p"]:
@@ -238,8 +234,12 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
"""Handles listitem tags (li)."""
nested_list = element.find(["ul", "ol"])
parent_list_label = self.parents[self.level].label
index_in_list = len(self.parents[self.level].children) + 1
parent = self.parents[self.level]
if parent is None:
_log.warning(f"list-item has no parent in DoclingDocument: {element}")
return
parent_label: str = parent.label
index_in_list = len(parent.children) + 1
if nested_list:
# Text in list item can be hidden within hierarchy, hence
@@ -251,7 +251,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
marker = ""
enumerated = False
if parent_list_label == GroupLabel.ORDERED_LIST:
if parent_label == GroupLabel.ORDERED_LIST:
marker = str(index_in_list)
enumerated = True
@@ -261,7 +261,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
text=text,
enumerated=enumerated,
marker=marker,
parent=self.parents[self.level],
parent=parent,
)
self.level += 1
@@ -275,14 +275,14 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
marker = ""
enumerated = False
if parent_list_label == GroupLabel.ORDERED_LIST:
if parent_label == GroupLabel.ORDERED_LIST:
marker = f"{str(index_in_list)}."
enumerated = True
doc.add_list_item(
text=text,
enumerated=enumerated,
marker=marker,
parent=self.parents[self.level],
parent=parent,
)
else:
_log.warning(f"list-item has no text: {element}")