Pdf2docx: 压缩错误-2

创建于 2020-10-20  ·  9评论  ·  资料来源: dothinking/pdf2docx

遇到错误compression error -2 。 如果有人能够提供一些指示,那就太好了

附上问题的PDF:
5_EN.pdf

错误信息:

Processing Pages: 1/28...mupdf: compression error -2
Traceback (most recent call last):
  File "/Users/erikchan/Downloads/convert.py", line 10, in <module>
    parse(pdf_files[i], docx_files[i])
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pdf2docx/main.py", line 31, in parse
    cv.make_docx(indexes, multi_processing)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pdf2docx/converter.py", line 118, in make_docx
    self._make_docx(page_indexes)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pdf2docx/converter.py", line 192, in _make_docx
    self.initialize(page).parse().make_page(self.doc_docx)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pdf2docx/converter.py", line 172, in initialize
    images, paths = self._paths_extractor.extract_paths(page)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pdf2docx/shape/Path.py", line 61, in extract_paths
    image = largest.to_image(page) if largest.contains_curve else None
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pdf2docx/shape/Path.py", line 140, in to_image
    return ImagesExtractor.clip_page(page, bbox, zoom)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pdf2docx/image/Image.py", line 60, in clip_page
    return cls.to_raw_dict(image, bbox)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pdf2docx/image/Image.py", line 50, in to_raw_dict
    'image': image.getPNGData()
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/fitz/fitz.py", line 5899, in getPNGData
    barray = self._getImageData(1)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/fitz/fitz.py", line 5868, in _getImageData
    return _fitz.Pixmap__getImageData(self, format)
RuntimeError: compression error -2

bug enhancement

最有用的评论

似乎带有python-docx浮动图片是一个常见的请求,文档在这里共享。

# -*- coding: utf-8 -*-

'''
Implement floating image based on python-docx.

- Text wrapping style: BEHIND TEXT <wp:anchor behindDoc="1">
- Picture position: top-left corner of PAGE `<wp:positionH relativeFrom="page">`.

Create a docx sample (Layout | Positions | More Layout Options) and explore the 
source xml (Open as a zip | word | document.xml) to implement other text wrapping
styles and position modes per `CT_Anchor._anchor_xml()`.
'''

from docx.oxml import parse_xml, register_element_cls
from docx.oxml.ns import nsdecls
from docx.oxml.shape import CT_Picture
from docx.oxml.xmlchemy import BaseOxmlElement, OneAndOnlyOne

# refer to docx.oxml.shape.CT_Inline
class CT_Anchor(BaseOxmlElement):
    """
    ``<w:anchor>`` element, container for a floating image.
    """
    extent = OneAndOnlyOne('wp:extent')
    docPr = OneAndOnlyOne('wp:docPr')
    graphic = OneAndOnlyOne('a:graphic')

    <strong i="7">@classmethod</strong>
    def new(cls, cx, cy, shape_id, pic, pos_x, pos_y):
        """
        Return a new ``<wp:anchor>`` element populated with the values passed
        as parameters.
        """
        anchor = parse_xml(cls._anchor_xml(pos_x, pos_y))
        anchor.extent.cx = cx
        anchor.extent.cy = cy
        anchor.docPr.id = shape_id
        anchor.docPr.name = 'Picture %d' % shape_id
        anchor.graphic.graphicData.uri = (
            'http://schemas.openxmlformats.org/drawingml/2006/picture'
        )
        anchor.graphic.graphicData._insert_pic(pic)
        return anchor

    <strong i="8">@classmethod</strong>
    def new_pic_anchor(cls, shape_id, rId, filename, cx, cy, pos_x, pos_y):
        """
        Return a new `wp:anchor` element containing the `pic:pic` element
        specified by the argument values.
        """
        pic_id = 0  # Word doesn't seem to use this, but does not omit it
        pic = CT_Picture.new(pic_id, filename, rId, cx, cy)
        anchor = cls.new(cx, cy, shape_id, pic, pos_x, pos_y)
        anchor.graphic.graphicData._insert_pic(pic)
        return anchor

    <strong i="9">@classmethod</strong>
    def _anchor_xml(cls, pos_x, pos_y):
        return (
            '<wp:anchor distT="0" distB="0" distL="0" distR="0" simplePos="0" relativeHeight="0" \n'
            '           behindDoc="1" locked="0" layoutInCell="1" allowOverlap="1" \n'
            '           %s>\n'
            '  <wp:simplePos x="0" y="0"/>\n'
            '  <wp:positionH relativeFrom="page">\n'
            '    <wp:posOffset>%d</wp:posOffset>\n'
            '  </wp:positionH>\n'
            '  <wp:positionV relativeFrom="page">\n'
            '    <wp:posOffset>%d</wp:posOffset>\n'
            '  </wp:positionV>\n'                    
            '  <wp:extent cx="914400" cy="914400"/>\n'
            '  <wp:wrapNone/>\n'
            '  <wp:docPr id="666" name="unnamed"/>\n'
            '  <wp:cNvGraphicFramePr>\n'
            '    <a:graphicFrameLocks noChangeAspect="1"/>\n'
            '  </wp:cNvGraphicFramePr>\n'
            '  <a:graphic>\n'
            '    <a:graphicData uri="URI not set"/>\n'
            '  </a:graphic>\n'
            '</wp:anchor>' % ( nsdecls('wp', 'a', 'pic', 'r'), int(pos_x), int(pos_y) )
        )


# refer to docx.parts.story.BaseStoryPart.new_pic_inline
def new_pic_anchor(part, image_descriptor, width, height, pos_x, pos_y):
    """Return a newly-created `w:anchor` element.

    The element contains the image specified by *image_descriptor* and is scaled
    based on the values of *width* and *height*.
    """
    rId, image = part.get_or_add_image(image_descriptor)
    cx, cy = image.scaled_dimensions(width, height)
    shape_id, filename = part.next_id, image.filename    
    return CT_Anchor.new_pic_anchor(shape_id, rId, filename, cx, cy, pos_x, pos_y)


# refer to docx.text.run.add_picture
def add_float_picture(p, image_path_or_stream, width=None, height=None, pos_x=0, pos_y=0):
    """Add float picture at fixed position `pos_x` and `pos_y` to the top-left point of page.
    """
    run = p.add_run()
    anchor = new_pic_anchor(run.part, image_path_or_stream, width, height, pos_x, pos_y)
    run._r.add_drawing(anchor)

# refer to docx.oxml.shape.__init__.py
register_element_cls('wp:anchor', CT_Anchor)


if __name__ == '__main__':

    from docx import Document
    from docx.shared import Inches, Pt

    document = Document()

    # add a floating image
    p = document.add_paragraph()
    add_float_picture(p, 'test.png', width=Inches(5.0), pos_x=Pt(20), pos_y=Pt(30))

    # add text
    p.add_run('Hello World'*50)


    document.save('output.docx')

所有9条评论

感谢您提供此案例。

许多矢量图形,即path像一条线、曲线和它们的组合,存在于您的 pdf 中。 但是,由于从 pdf 中提取这些路径时的技术问题,当前该库会忽略剪切路径。 一些路径在没有被剪切的情况下超出页面,这导致了compression error -2问题。

此外,转换这个pdf还有两个问题:

  • 路径颜色不正确。 我想根本原因是目前只考虑了Device Color Space (Gray/RGB/CMYK),而这个 pdf 样本可能遵循特殊的色彩空间,如Indexed CS , DeviceN CS

  • 重叠的图像被删除。 python-docx用于编写转换后的 docx,但python-docx现在不支持浮动元素。 因此,作为妥协,浮动图像被删除。

因此,不幸的是, pdf2docx暂时无法转换您的 pdf。 至少应该做出以下努力:

  • 从pdf中提取路径时的剪辑路径
  • 实现更多色彩空间
  • 介绍浮动图像

感谢@dothinking的清晰解释。 我很惊讶这个库并没有比现在更受欢迎。 当前版本已经非常好,我知道很多人可以从中受益。

请让我知道我可以如何帮助解决您列出的任何问题(我需要一些指导。)无论是解决错误、测试还是其他问题。

非常感谢@echan00。

关于这个问题的一些进展:

  • [x]支持浮动图像
  • [ ] 剪辑路径和色彩空间 -> 另一个上游库PyMuPDF发布了关于提取路径的新功能的好消息。 我会研究它,希望可以解决这个问题。

之后,任何测试或建议表示赞赏。

2020-12-31 评论:最新的PyMuPDF 1.18.5 部分解决了这个问题,但并不完美,尤其是剪切路径。

由于python-docx支持内嵌图像,因此探索浮动图像的步骤:

  • 创建两个 docx 文件,一个带有内嵌图像,另一个带有浮动图像(对于这种情况, behind text模式)
  • 检查这两个文件之间源xml的差异
  • 基于观察到的结构和内联图像代码实现浮动图像

xml结构结果:

  • 内嵌图像是<wp:inline>下节点<w:drawing>
  • 浮动图像是<wp:anchor>下节点<w:drawing>
  • 除了内嵌图片的所有子节点外,浮动图片还包含<wp:positionH><wp:positionV>来定义固定位置

所以,这个想法是创建<wp:anchor>节点,然后附加子节点:

  • 所有节点与内嵌图像相同
  • <wp:positionH><wp:positionV>

似乎带有python-docx浮动图片是一个常见的请求,文档在这里共享。

# -*- coding: utf-8 -*-

'''
Implement floating image based on python-docx.

- Text wrapping style: BEHIND TEXT <wp:anchor behindDoc="1">
- Picture position: top-left corner of PAGE `<wp:positionH relativeFrom="page">`.

Create a docx sample (Layout | Positions | More Layout Options) and explore the 
source xml (Open as a zip | word | document.xml) to implement other text wrapping
styles and position modes per `CT_Anchor._anchor_xml()`.
'''

from docx.oxml import parse_xml, register_element_cls
from docx.oxml.ns import nsdecls
from docx.oxml.shape import CT_Picture
from docx.oxml.xmlchemy import BaseOxmlElement, OneAndOnlyOne

# refer to docx.oxml.shape.CT_Inline
class CT_Anchor(BaseOxmlElement):
    """
    ``<w:anchor>`` element, container for a floating image.
    """
    extent = OneAndOnlyOne('wp:extent')
    docPr = OneAndOnlyOne('wp:docPr')
    graphic = OneAndOnlyOne('a:graphic')

    <strong i="7">@classmethod</strong>
    def new(cls, cx, cy, shape_id, pic, pos_x, pos_y):
        """
        Return a new ``<wp:anchor>`` element populated with the values passed
        as parameters.
        """
        anchor = parse_xml(cls._anchor_xml(pos_x, pos_y))
        anchor.extent.cx = cx
        anchor.extent.cy = cy
        anchor.docPr.id = shape_id
        anchor.docPr.name = 'Picture %d' % shape_id
        anchor.graphic.graphicData.uri = (
            'http://schemas.openxmlformats.org/drawingml/2006/picture'
        )
        anchor.graphic.graphicData._insert_pic(pic)
        return anchor

    <strong i="8">@classmethod</strong>
    def new_pic_anchor(cls, shape_id, rId, filename, cx, cy, pos_x, pos_y):
        """
        Return a new `wp:anchor` element containing the `pic:pic` element
        specified by the argument values.
        """
        pic_id = 0  # Word doesn't seem to use this, but does not omit it
        pic = CT_Picture.new(pic_id, filename, rId, cx, cy)
        anchor = cls.new(cx, cy, shape_id, pic, pos_x, pos_y)
        anchor.graphic.graphicData._insert_pic(pic)
        return anchor

    <strong i="9">@classmethod</strong>
    def _anchor_xml(cls, pos_x, pos_y):
        return (
            '<wp:anchor distT="0" distB="0" distL="0" distR="0" simplePos="0" relativeHeight="0" \n'
            '           behindDoc="1" locked="0" layoutInCell="1" allowOverlap="1" \n'
            '           %s>\n'
            '  <wp:simplePos x="0" y="0"/>\n'
            '  <wp:positionH relativeFrom="page">\n'
            '    <wp:posOffset>%d</wp:posOffset>\n'
            '  </wp:positionH>\n'
            '  <wp:positionV relativeFrom="page">\n'
            '    <wp:posOffset>%d</wp:posOffset>\n'
            '  </wp:positionV>\n'                    
            '  <wp:extent cx="914400" cy="914400"/>\n'
            '  <wp:wrapNone/>\n'
            '  <wp:docPr id="666" name="unnamed"/>\n'
            '  <wp:cNvGraphicFramePr>\n'
            '    <a:graphicFrameLocks noChangeAspect="1"/>\n'
            '  </wp:cNvGraphicFramePr>\n'
            '  <a:graphic>\n'
            '    <a:graphicData uri="URI not set"/>\n'
            '  </a:graphic>\n'
            '</wp:anchor>' % ( nsdecls('wp', 'a', 'pic', 'r'), int(pos_x), int(pos_y) )
        )


# refer to docx.parts.story.BaseStoryPart.new_pic_inline
def new_pic_anchor(part, image_descriptor, width, height, pos_x, pos_y):
    """Return a newly-created `w:anchor` element.

    The element contains the image specified by *image_descriptor* and is scaled
    based on the values of *width* and *height*.
    """
    rId, image = part.get_or_add_image(image_descriptor)
    cx, cy = image.scaled_dimensions(width, height)
    shape_id, filename = part.next_id, image.filename    
    return CT_Anchor.new_pic_anchor(shape_id, rId, filename, cx, cy, pos_x, pos_y)


# refer to docx.text.run.add_picture
def add_float_picture(p, image_path_or_stream, width=None, height=None, pos_x=0, pos_y=0):
    """Add float picture at fixed position `pos_x` and `pos_y` to the top-left point of page.
    """
    run = p.add_run()
    anchor = new_pic_anchor(run.part, image_path_or_stream, width, height, pos_x, pos_y)
    run._r.add_drawing(anchor)

# refer to docx.oxml.shape.__init__.py
register_element_cls('wp:anchor', CT_Anchor)


if __name__ == '__main__':

    from docx import Document
    from docx.shared import Inches, Pt

    document = Document()

    # add a floating image
    p = document.add_paragraph()
    add_float_picture(p, 'test.png', width=Inches(5.0), pos_x=Pt(20), pos_y=Pt(30))

    # add text
    p.add_run('Hello World'*50)


    document.save('output.docx')

不错的@dothinking ,看起来您知道问题到底是什么。 我有各种各样的 PDF,一旦你准备好,我可以帮助测试

@dothinking 非常感谢您的代码示例! 完美解决我的问题!!!!

好久没时间做这个项目了。 新版本v0.5.0现在可以部分解决这个问题:

  • 现在支持浮动图像。
  • 上游库PyMuPDF支持路径提取,但对于复杂的形状(例如剪切路径)不太好。

使用这个最新版本,示例pdf可以成功转换,但由于复杂/华丽的风格,仍然需要大量工作来提高转换后的docx文件的质量。

哇,这是一个伟大的升级。 非常感谢您的辛勤工作@dothinking

此页面是否有帮助?
0 / 5 - 0 等级