langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 12:05:30 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

The .docx file parsing cannot handle images within tables, and when dealing with merged cells, duplicate content may appear. #4865

New Issue
Closed
opened 2026-02-21 18:08:21 -05:00 by yindo · 1 comment
yindo commented 2026-02-21 18:08:21 -05:00
Owner
Copy Link
Copy Source

Originally created by @huixiangyang on GitHub (Aug 2, 2024).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
  • Please do not modify this template :) and fill in all the required fields.

Dify version

0.6.15

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

The image in the table cannot be parsed, and the content across columns will be parsed repeatedly.
image

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

Originally created by @huixiangyang on GitHub (Aug 2, 2024). ### Self Checks - [X] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [X] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:） - [X] Please do not modify this template :) and fill in all the required fields. ### Dify version 0.6.15 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce The image in the table cannot be parsed, and the content across columns will be parsed repeatedly. ![image](https://github.com/user-attachments/assets/3152f866-29f4-490a-aea9-195070e3e9bc) ### ✔️ Expected Behavior _No response_ ### ❌ Actual Behavior _No response_
yindo added the 🐞 bug label 2026-02-21 18:08:21 -05:00
yindo closed this issue 2026-02-21 18:08:21 -05:00
yindo commented 2026-02-21 18:08:22 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Aug 2, 2024):

@yanghx-git Hello there! I'm here to assist you with any bugs, questions, or contributions while we wait for a human maintainer. Let me know how I can help you today.

To resolve the issue with the .docx file parser in Dify version 0.6.15, where images within table cells are not parsed and content in merged cells is duplicated, you need to make the following changes:

  1. Ensure images within table cells are parsed: Modify the _table_to_markdown method to include image extraction logic.
  2. Handle merged cells properly: Update the _table_to_markdown method to avoid duplicating content in merged cells.

Here is the updated code for the _table_to_markdown method:

def _table_to_markdown(self, table, image_map):
    markdown = ""
    # deal with table headers
    header_row = table.rows[0]
    headers = [self._parse_cell(cell, image_map) for cell in header_row.cells]
    markdown += "| " + " | ".join(headers) + " |\n"
    markdown += "| " + " | ".join(["---"] * len(headers)) + " |\n"
    # deal with table rows
    for row in table.rows[1:]:
        row_cells = [self._parse_cell(cell, image_map) for cell in row.cells]
        markdown += "| " + " | ".join(row_cells) + " |\n"

    return markdown

def _parse_cell(self, cell, image_map):
    cell_content = []
    for paragraph in cell.paragraphs:
        cell_content.append(self._parse_paragraph(paragraph, image_map))
    return ' '.join(cell_content).strip()

Additionally, ensure that the parse_docx method calls _table_to_markdown with the image_map parameter:

def parse_docx(self, docx_path, image_folder):
    doc = DocxDocument(docx_path)
    os.makedirs(image_folder, exist_ok=True)

    content = []

    image_map = self._extract_images_from_docx(doc, image_folder)

    def parse_paragraph(paragraph):
        paragraph_content = []
        for run in paragraph.runs:
            if run.element.tag.endswith('r'):
                drawing_elements = run.element.findall(
                    './/{http://schemas.openxmlformats.org/wordprocessingml/2006/main}drawing')
                for drawing in drawing_elements:
                    blip_elements = drawing.findall(
                        './/{http://schemas.openxmlformats.org/drawingml/2006/main}blip')
                    for blip in blip_elements:
                        embed_id = blip.get(
                            '{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed')
                        if embed_id:
                            image_part = doc.part.related_parts.get(embed_id)
                            if image_part in image_map:
                                paragraph_content.append(image_map[image_part])
            if run.text.strip():
                paragraph_content.append(run.text.strip())
        return ''.join(paragraph_content) if paragraph_content else ''

    paragraphs = doc.paragraphs.copy()
    tables = doc.tables.copy()
    for element in doc.element.body:
        if element.tag.endswith('p'):  # paragraph
            para = paragraphs.pop(0)
            parsed_paragraph = parse_paragraph(para)
            if parsed_paragraph:
                content.append(parsed_paragraph)
        elif element.tag.endswith('tbl'):  # table
            table = tables.pop(0)
            content.append(self._table_to_markdown(table, image_map))
    return '\n'.join(content)

These changes should address the issues with images within table cells not being parsed and content in merged cells being duplicated [1].

To continue talking to Dosu, mention @dosu.

@dosubot[bot] commented on GitHub (Aug 2, 2024): <!-- Greeting --> @yanghx-git Hello there! I'm here to assist you with any bugs, questions, or contributions while we wait for a human maintainer. Let me know how I can help you today. <!-- Answer --> To resolve the issue with the .docx file parser in Dify version 0.6.15, where images within table cells are not parsed and content in merged cells is duplicated, you need to make the following changes: 1. **Ensure images within table cells are parsed**: Modify the `_table_to_markdown` method to include image extraction logic. 2. **Handle merged cells properly**: Update the `_table_to_markdown` method to avoid duplicating content in merged cells. Here is the updated code for the `_table_to_markdown` method: ```python def _table_to_markdown(self, table, image_map): markdown = "" # deal with table headers header_row = table.rows[0] headers = [self._parse_cell(cell, image_map) for cell in header_row.cells] markdown += "| " + " | ".join(headers) + " |\n" markdown += "| " + " | ".join(["---"] * len(headers)) + " |\n" # deal with table rows for row in table.rows[1:]: row_cells = [self._parse_cell(cell, image_map) for cell in row.cells] markdown += "| " + " | ".join(row_cells) + " |\n" return markdown def _parse_cell(self, cell, image_map): cell_content = [] for paragraph in cell.paragraphs: cell_content.append(self._parse_paragraph(paragraph, image_map)) return ' '.join(cell_content).strip() ``` Additionally, ensure that the `parse_docx` method calls `_table_to_markdown` with the `image_map` parameter: ```python def parse_docx(self, docx_path, image_folder): doc = DocxDocument(docx_path) os.makedirs(image_folder, exist_ok=True) content = [] image_map = self._extract_images_from_docx(doc, image_folder) def parse_paragraph(paragraph): paragraph_content = [] for run in paragraph.runs: if run.element.tag.endswith('r'): drawing_elements = run.element.findall( './/{http://schemas.openxmlformats.org/wordprocessingml/2006/main}drawing') for drawing in drawing_elements: blip_elements = drawing.findall( './/{http://schemas.openxmlformats.org/drawingml/2006/main}blip') for blip in blip_elements: embed_id = blip.get( '{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed') if embed_id: image_part = doc.part.related_parts.get(embed_id) if image_part in image_map: paragraph_content.append(image_map[image_part]) if run.text.strip(): paragraph_content.append(run.text.strip()) return ''.join(paragraph_content) if paragraph_content else '' paragraphs = doc.paragraphs.copy() tables = doc.tables.copy() for element in doc.element.body: if element.tag.endswith('p'): # paragraph para = paragraphs.pop(0) parsed_paragraph = parse_paragraph(para) if parsed_paragraph: content.append(parsed_paragraph) elif element.tag.endswith('tbl'): # table table = tables.pop(0) content.append(self._table_to_markdown(table, image_map)) return '\n'.join(content) ``` These changes should address the issues with images within table cells not being parsed and content in merged cells being duplicated <sup>[[1]](https://github.com/langgenius/dify/blob/main/api/core/rag/extractor/word_extractor.py)</sup>. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.*
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#4865
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?