NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ci: add coverage and ruff (#1383)

Browse Source 
* add coverage calculation and push

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* new codecov version and usage of token

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* enable ruff formatter instead of black and isort

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* apply ruff lint fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* apply ruff unsafe fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add removed imports

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* runs 1 on linter issues

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* finalize linter fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Update pyproject.toml

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

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Michele Dolfi
2025-04-14 18:01:26 +02:00
committed by GitHub
parent 293c28ca7c
commit 5458a88464
104 changed files with 665 additions and 633 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
docling/backend/html_backend.py
View File

@@ -55,7 +55,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
self.max_levels = 10
self.level = 0
self.parents: dict[int, Optional[Union[DocItem, GroupItem]]] = {}
for i in range(0, self.max_levels):
for i in range(self.max_levels):
self.parents[i] = None
try:
@@ -126,7 +126,6 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
return doc
def walk(self, tag: Tag, doc: DoclingDocument) -> None:
# Iterate over elements in the body of the document
text: str = ""
for element in tag.children:
@@ -135,7 +134,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
self.analyze_tag(cast(Tag, element), doc)
except Exception as exc_child:
_log.error(
f"Error processing child from tag {tag.name}: {repr(exc_child)}"
f"Error processing child from tag {tag.name}: {exc_child!r}"
)
raise exc_child
elif isinstance(element, NavigableString) and not isinstance(
@@ -147,7 +146,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
item for item in element.next_siblings if isinstance(item, Tag)
]
if element.next_sibling is None or any(
[item.name in TAGS_FOR_NODE_ITEMS for item in siblings]
item.name in TAGS_FOR_NODE_ITEMS for item in siblings
):
text = text.strip()
if text and tag.name in ["div"]:
@@ -222,7 +221,6 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
)
else:
if hlevel > self.level:
# add invisible group
for i in range(self.level + 1, hlevel):
self.parents[i] = doc.add_group(
@@ -234,7 +232,6 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
self.level = hlevel
elif hlevel < self.level:
# remove the tail
for key in self.parents.keys():
if key > hlevel:
@@ -360,7 +357,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
marker = ""
enumerated = False
if parent_label == GroupLabel.ORDERED_LIST:
marker = f"{str(index_in_list)}."
marker = f"{index_in_list!s}."
enumerated = True
doc.add_list_item(
text=text,