Skip to content

fix: parse pdf file null char not allowed. #6221

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Binx98 wants to merge 1 commit into
base: v2
Choose a base branch
from
+16 −8
Open

fix: parse pdf file null char not allowed. #6221

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions apps/common/handle/impl/text/pdf_split_handle.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,7 +228,7 @@ def collect_toc(doc, outline, level, toc):
title = item.get("/Title")
if title is None:
title = str(item)
toc.append((level, str(title), page_number))
toc.append((level, str(title).replace("\0", ""), page_number))

@staticmethod
def handle_toc(doc, limit):
Expand Down Expand Up @@ -522,7 +522,7 @@ def visitor_text(text, cm, tm, font_dict, font_size):
except BaseException:
return ""

return "".join(text_parts).strip().split("\n")[0].replace(".", "").strip()
return "".join(text_parts).replace("\0", "").strip().split("\n")[0].replace(".", "").strip()

@staticmethod
def extract_first_line(page):
Expand All @@ -531,6 +531,7 @@ def extract_first_line(page):

@staticmethod
def handle_chapter_title(title):
title = title.replace("\0", "")
title = re.sub(r"[一二三四五六七八九十\s*]、\s*", "", title)
title = re.sub(r"第[一二三四五六七八九十]章\s*", "", title)
return title
Expand Down
19 changes: 13 additions & 6 deletions apps/knowledge/serializers/paragraph.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,13 @@
from knowledge.task.generate import generate_related_by_paragraph_id_list


class NullCharacterStrippedCharField(serializers.CharField):
def to_internal_value(self, data):
if isinstance(data, str):
data = data.replace("\x00", "")
return super().to_internal_value(data)


class ParagraphSerializer(serializers.ModelSerializer):
class Meta:
model = Paragraph
Expand All @@ -59,21 +66,21 @@ class ParagraphInstanceSerializer(serializers.Serializer):
段落实例对象
"""

content = serializers.CharField(
content = NullCharacterStrippedCharField(
required=True, label=_("content"), max_length=102400, min_length=1, allow_null=True, allow_blank=True
)
title = serializers.CharField(
title = NullCharacterStrippedCharField(
required=False, max_length=256, label=_("section title"), allow_null=True, allow_blank=True
)
problem_list = ProblemInstanceSerializer(required=False, many=True)
is_active = serializers.BooleanField(required=False, label=_("Is active"))


class EditParagraphSerializers(serializers.Serializer):
title = serializers.CharField(
title = NullCharacterStrippedCharField(
required=False, max_length=256, label=_("section title"), allow_null=True, allow_blank=True
)
content = serializers.CharField(
content = NullCharacterStrippedCharField(
required=False, max_length=102400, allow_null=True, allow_blank=True, label=_("section title")
)
problem_list = ProblemInstanceSerializer(required=False, many=True)
Expand All @@ -91,10 +98,10 @@ class ParagraphBatchGenerateRelatedSerializer(serializers.Serializer):


class ParagraphSerializers(serializers.Serializer):
title = serializers.CharField(
title = NullCharacterStrippedCharField(
required=False, max_length=256, label=_("section title"), allow_null=True, allow_blank=True
)
content = serializers.CharField(required=True, max_length=102400, label=_("section title"))
content = NullCharacterStrippedCharField(required=True, max_length=102400, label=_("section title"))

class Problem(serializers.Serializer):
workspace_id = serializers.CharField(required=True, label=_("workspace id"))
Expand Down