Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ac49ad1bcf | ||
|
|
d74bf1eaa9 | ||
|
|
cf3c89bf25 | ||
|
|
b491cd2181 | ||
|
|
70144c8fe1 | ||
|
|
0d832bf7fa | ||
|
|
7319b7f584 | ||
|
|
5b641d6243 | ||
|
|
10d679d379 | ||
|
|
5378a4f34c | ||
|
|
42cbc8e39e | ||
|
|
66004988f4 | ||
|
|
7722b99f70 | ||
|
|
66b5fea65c | ||
|
|
659b19dae9 | ||
|
|
337c1b4a76 | ||
|
|
76deefb9dc | ||
|
|
e51618231d |
No files matched your search
@@ -1,4 +1,15 @@
|
||||
# PDFMajor
|
||||
# PDFMajor
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<td>Latest Release</td>
|
||||
<td>
|
||||
<a href="https://pypi.org/project/pdfmajor/">
|
||||
<img src="https://img.shields.io/pypi/v/pdfmajor.svg" alt="latest release" />
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
PDF-Major is a fork of `PDFMiner.six`. It is meant to be a more light-weight implementation that makes fewer assumptions on the data. Additionally, this version intends to be more up to date with recent versions of python and make liberal use of the typing capabilities of python for improved future maintainability.
|
||||
|
||||
|
||||
+9
-1
@@ -4,7 +4,15 @@ WK_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
|
||||
cd $WK_DIR
|
||||
cd ..
|
||||
|
||||
sh bin/clean/sh
|
||||
./bin/clean.sh
|
||||
|
||||
python setup.py sdist bdist_wheel
|
||||
|
||||
git add .
|
||||
git commit
|
||||
git push
|
||||
|
||||
git tag $(cat .version)
|
||||
git push -u origin $(cat .version)
|
||||
|
||||
twine upload dist/*
|
||||
@@ -27,3 +27,7 @@ def update_pdfmajor__init___(version: str, doc: str):
|
||||
long_description=doc,
|
||||
version_tuple=re.sub(r"\.", ", ", version, count=2)
|
||||
))
|
||||
|
||||
def update_current_version_lock(version: str):
|
||||
with open(".version", 'w') as file:
|
||||
file.write("v"+version)
|
||||
+12
-1
@@ -1,4 +1,15 @@
|
||||
# PDFMajor
|
||||
# PDFMajor
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<td>Latest Release</td>
|
||||
<td>
|
||||
<a href="https://pypi.org/project/pdfmajor/">
|
||||
<img src="https://img.shields.io/pypi/v/pdfmajor.svg" alt="latest release" />
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
PDF-Major is a fork of `PDFMiner.six`. It is meant to be a more light-weight implementation that makes fewer assumptions on the data. Additionally, this version intends to be more up to date with recent versions of python and make liberal use of the typing capabilities of python for improved future maintainability.
|
||||
|
||||
|
||||
+14
-3
@@ -53,7 +53,7 @@
|
||||
<a class="current" href=".">Home</a>
|
||||
<ul class="subnav">
|
||||
|
||||
<li class="toctree-l2"><a href="#pdf-major">PDF-Major</a></li>
|
||||
<li class="toctree-l2"><a href="#pdfmajor">PDFMajor</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
@@ -110,7 +110,18 @@
|
||||
<div role="main">
|
||||
<div class="section">
|
||||
|
||||
<h1 id="pdf-major">PDF-Major</h1>
|
||||
<h1 id="pdfmajor">PDFMajor</h1>
|
||||
<table>
|
||||
<tr>
|
||||
<td>Latest Release</td>
|
||||
<td>
|
||||
<a href="https://pypi.org/project/pdfmajor/">
|
||||
<img src="https://img.shields.io/pypi/v/pdfmajor.svg" alt="latest release" />
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
<p>PDF-Major is a fork of <code>PDFMiner.six</code>. It is meant to be a more light-weight implementation that makes fewer assumptions on the data. Additionally, this version intends to be more up to date with recent versions of python and make liberal use of the typing capabilities of python for improved future maintainability.</p>
|
||||
<h2 id="documentation">Documentation</h2>
|
||||
<p>See documentation <a href="https://asosnovsky.github.io/pdfmajor/">here</a>.</p>
|
||||
@@ -216,5 +227,5 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.</p>
|
||||
|
||||
<!--
|
||||
MkDocs version : 1.0.4
|
||||
Build Date UTC : 2018-10-12 22:22:34
|
||||
Build Date UTC : 2018-11-04 21:27:38
|
||||
-->
|
||||
@@ -1 +1 @@
|
||||
{"config":{"lang":["en"],"prebuild_index":false,"separator":"[\\s\\-]+"},"docs":[{"location":"","text":"PDF-Major PDF-Major is a fork of PDFMiner.six . It is meant to be a more light-weight implementation that makes fewer assumptions on the data. Additionally, this version intends to be more up to date with recent versions of python and make liberal use of the typing capabilities of python for improved future maintainability. Documentation See documentation here . Why Another Fork? PDFMiner was designed to run in python 2.7>, PDFMiner.six was written to bring cross-version support for python 2 and 3. This versions intends to make use of the latest improvement in the python language while remaining fairly simple to develop with. Features Written entirely in Python. Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Font-Color extraction Shape fill and stroke color extraction Note : We took out the layout-analysis process in this version (there is no more LTTextHorizontal or LTTextVertical). While the mathematics behind the grouping process was sound, the coupling of the layout-analysis process with the parsing and interpretation process produced unfriendly-code. This feature could be brought back by extending the pdfmajor.layouts.PDFLayoutAnalyzer class, but at the current time is not supported. How to Install Source Install Python 3.6.4 or newer. clone this repo git clone https://github.com/asosnovsky/pdfmajor * install repo python setup.py install Pypi Install Python 3.6.4 or newer. install repo pip install pdfmajor Terms and Conditions (This is so-called MIT/X License) Copyright (c) 2018-2019 Ariel Sosnovsky Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the \"Software\"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.","title":"Home"},{"location":"#pdf-major","text":"PDF-Major is a fork of PDFMiner.six . It is meant to be a more light-weight implementation that makes fewer assumptions on the data. Additionally, this version intends to be more up to date with recent versions of python and make liberal use of the typing capabilities of python for improved future maintainability.","title":"PDF-Major"},{"location":"#documentation","text":"See documentation here .","title":"Documentation"},{"location":"#why-another-fork","text":"PDFMiner was designed to run in python 2.7>, PDFMiner.six was written to bring cross-version support for python 2 and 3. This versions intends to make use of the latest improvement in the python language while remaining fairly simple to develop with.","title":"Why Another Fork?"},{"location":"#features","text":"Written entirely in Python. Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Font-Color extraction Shape fill and stroke color extraction Note : We took out the layout-analysis process in this version (there is no more LTTextHorizontal or LTTextVertical). While the mathematics behind the grouping process was sound, the coupling of the layout-analysis process with the parsing and interpretation process produced unfriendly-code. This feature could be brought back by extending the pdfmajor.layouts.PDFLayoutAnalyzer class, but at the current time is not supported.","title":"Features"},{"location":"#how-to-install","text":"","title":"How to Install"},{"location":"#source","text":"Install Python 3.6.4 or newer. clone this repo git clone https://github.com/asosnovsky/pdfmajor * install repo python setup.py install","title":"Source"},{"location":"#pypi","text":"Install Python 3.6.4 or newer. install repo pip install pdfmajor","title":"Pypi"},{"location":"#terms-and-conditions","text":"(This is so-called MIT/X License) Copyright (c) 2018-2019 Ariel Sosnovsky Permission is hereby granted, free of charge, to any person obtaining aLine truncated
|
||||
{"config":{"lang":["en"],"prebuild_index":false,"separator":"[\\s\\-]+"},"docs":[{"location":"","text":"PDFMajor Latest Release PDF-Major is a fork of PDFMiner.six . It is meant to be a more light-weight implementation that makes fewer assumptions on the data. Additionally, this version intends to be more up to date with recent versions of python and make liberal use of the typing capabilities of python for improved future maintainability. Documentation See documentation here . Why Another Fork? PDFMiner was designed to run in python 2.7>, PDFMiner.six was written to bring cross-version support for python 2 and 3. This versions intends to make use of the latest improvement in the python language while remaining fairly simple to develop with. Features Written entirely in Python. Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Font-Color extraction Shape fill and stroke color extraction Note : We took out the layout-analysis process in this version (there is no more LTTextHorizontal or LTTextVertical). While the mathematics behind the grouping process was sound, the coupling of the layout-analysis process with the parsing and interpretation process produced unfriendly-code. This feature could be brought back by extending the pdfmajor.layouts.PDFLayoutAnalyzer class, but at the current time is not supported. How to Install Source Install Python 3.6.4 or newer. clone this repo git clone https://github.com/asosnovsky/pdfmajor * install repo python setup.py install Pypi Install Python 3.6.4 or newer. install repo pip install pdfmajor Terms and Conditions (This is so-called MIT/X License) Copyright (c) 2018-2019 Ariel Sosnovsky Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the \"Software\"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.","title":"Home"},{"location":"#pdfmajor","text":"Latest Release PDF-Major is a fork of PDFMiner.six . It is meant to be a more light-weight implementation that makes fewer assumptions on the data. Additionally, this version intends to be more up to date with recent versions of python and make liberal use of the typing capabilities of python for improved future maintainability.","title":"PDFMajor"},{"location":"#documentation","text":"See documentation here .","title":"Documentation"},{"location":"#why-another-fork","text":"PDFMiner was designed to run in python 2.7>, PDFMiner.six was written to bring cross-version support for python 2 and 3. This versions intends to make use of the latest improvement in the python language while remaining fairly simple to develop with.","title":"Why Another Fork?"},{"location":"#features","text":"Written entirely in Python. Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Font-Color extraction Shape fill and stroke color extraction Note : We took out the layout-analysis process in this version (there is no more LTTextHorizontal or LTTextVertical). While the mathematics behind the grouping process was sound, the coupling of the layout-analysis process with the parsing and interpretation process produced unfriendly-code. This feature could be brought back by extending the pdfmajor.layouts.PDFLayoutAnalyzer class, but at the current time is not supported.","title":"Features"},{"location":"#how-to-install","text":"","title":"How to Install"},{"location":"#source","text":"Install Python 3.6.4 or newer. clone this repo git clone https://github.com/asosnovsky/pdfmajor * install repo python setup.py install","title":"Source"},{"location":"#pypi","text":"Install Python 3.6.4 or newer. install repo pip install pdfmajor","title":"Pypi"},{"location":"#terms-and-conditions","text":"(This is so-called MIT/X License) Copyright (c) 2018-2019 Ariel Sosnovsky Permission is hereby granted, free of chargeLine truncated
|
||||
+2
-2
@@ -2,12 +2,12 @@
|
||||
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
|
||||
<url>
|
||||
<loc>None</loc>
|
||||
<lastmod>2018-10-12</lastmod>
|
||||
<lastmod>2018-11-04</lastmod>
|
||||
<changefreq>daily</changefreq>
|
||||
</url>
|
||||
<url>
|
||||
<loc>None</loc>
|
||||
<lastmod>2018-10-12</lastmod>
|
||||
<lastmod>2018-11-04</lastmod>
|
||||
<changefreq>daily</changefreq>
|
||||
</url>
|
||||
</urlset>
|
||||
Binary file not shown.
+13
-2
@@ -3,7 +3,18 @@
|
||||
# DO NOT EDIT THIS PAGE
|
||||
#
|
||||
"""
|
||||
# PDFMajor
|
||||
# PDFMajor
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<td>Latest Release</td>
|
||||
<td>
|
||||
<a href="https://pypi.org/project/pdfmajor/">
|
||||
<img src="https://img.shields.io/pypi/v/pdfmajor.svg" alt="latest release" />
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
PDF-Major is a fork of `PDFMiner.six`. It is meant to be a more light-weight implementation that makes fewer assumptions on the data. Additionally, this version intends to be more up to date with recent versions of python and make liberal use of the typing capabilities of python for improved future maintainability.
|
||||
|
||||
@@ -75,7 +86,7 @@ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
||||
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
|
||||
"""
|
||||
__version__ = (1, 1, 1)
|
||||
__version__ = (1, 1, 10)
|
||||
|
||||
if __name__ == '__main__':
|
||||
print(
|
||||
|
||||
@@ -26,6 +26,9 @@ def get_color(col: PDFGraphicStateColor):
|
||||
return f"cmyk({','.join(map(str, color_val))})"
|
||||
elif color_type == 'gray':
|
||||
return f'rgba(0,0,0,{1-color_val})'
|
||||
elif color_type == "custom":
|
||||
# Todo: convert these to more friendly color types
|
||||
return f"custom({col.custom['type']})"
|
||||
return "none"
|
||||
|
||||
class HTMLConverter(PDFConverter):
|
||||
@@ -42,8 +45,8 @@ class HTMLConverter(PDFConverter):
|
||||
self.__current_width = None
|
||||
self.write_header()
|
||||
|
||||
def write(self, text: str):
|
||||
text = " "*self.__levels_deep + text + '\n'
|
||||
def write(self, text: str, lineend: str = '\n', deep_space: str = ' '):
|
||||
text = deep_space*self.__levels_deep + text + lineend
|
||||
self.write_raw(text)
|
||||
|
||||
def write_raw(self, text):
|
||||
@@ -78,7 +81,13 @@ class HTMLConverter(PDFConverter):
|
||||
self.__levels_deep -= 1
|
||||
|
||||
@contextmanager
|
||||
def place_elm_with_child(self, tag_name: str, attr_dict: Dict[str, str] = {}, css: Dict[str, str] = None):
|
||||
def place_elm_with_child(self, tag_name: str, attr_dict: Dict[str, str] = {}, css: Dict[str, str] = None, no_additional_char = False):
|
||||
lineend = '\n'
|
||||
deep_space = ' '
|
||||
if no_additional_char:
|
||||
lineend = ''
|
||||
deep_space = ''
|
||||
|
||||
if css is not None:
|
||||
attr_dict['style'] = ";".join([
|
||||
f'{name}: {value}'
|
||||
@@ -88,11 +97,11 @@ class HTMLConverter(PDFConverter):
|
||||
f'{name}="{value}"'
|
||||
for name, value in attr_dict.items()
|
||||
])
|
||||
self.write(f"<{tag_name} {attrs}>")
|
||||
self.write(f"<{tag_name} {attrs}>", lineend=lineend)
|
||||
self.__levels_deep += 1
|
||||
yield
|
||||
self.__levels_deep -= 1
|
||||
self.write(f"</{tag_name}>")
|
||||
self.write(f"</{tag_name}>", deep_space=deep_space)
|
||||
|
||||
def place_elm_close(self, tag_name: str, attr_dict: Dict[str, str] = {}, css: Dict[str, str] = None, as_childless = True):
|
||||
if css is not None:
|
||||
@@ -201,28 +210,39 @@ class HTMLConverter(PDFConverter):
|
||||
self.place_image(item)
|
||||
elif isinstance(item, LTChar):
|
||||
with self.place_elm_with_child('span', { 'class': 'char' }, {
|
||||
'font-size': f'{item.size}px',
|
||||
'font-family': item.fontname,
|
||||
'font-weight': 'bold' if 'bold' in item.fontname.lower() else '',
|
||||
'color': get_color(item.graphicstate.ncolor),
|
||||
'position': 'absolute',
|
||||
'left': f'{item.x0}',
|
||||
'bottom': f'{item.y0}',
|
||||
'transform': f'skew({item.font.italic_angle}deg, 0deg)'
|
||||
'width': item.width,
|
||||
'min-width': item.width,
|
||||
'max-width': item.width,
|
||||
'height': item.height,
|
||||
'min-height': item.height,
|
||||
'max-height': item.height,
|
||||
}):
|
||||
self.write(item.get_text())
|
||||
elif isinstance(item, LTCharBlock):
|
||||
with self.place_elm_with_child('span', { 'class': 'char-block' }, {
|
||||
'font-size': f'{item.size}px',
|
||||
'font-family': item.fontname,
|
||||
'font-weight': 'bold' if 'bold' in item.fontname.lower() else '',
|
||||
'color': get_color(item.graphicstate.ncolor),
|
||||
'position': 'absolute',
|
||||
'left': f'{item.x0}',
|
||||
'bottom': f'{item.y0}',
|
||||
'transform': f'skew({item.font.italic_angle}deg, 0deg)'
|
||||
}):
|
||||
self.write(item.get_text())
|
||||
'position': 'absolute',
|
||||
'left': f'{item.x0}',
|
||||
'bottom': f'{item.y0}',
|
||||
'text-align': 'justify',
|
||||
'font-size': f'{item.size}px',
|
||||
'font-family': item.fontname,
|
||||
'font-weight': item.font.font_weight,
|
||||
'color': get_color(item.graphicstate.ncolor),
|
||||
'width': item.width,
|
||||
'min-width': item.width,
|
||||
'max-width': item.width,
|
||||
'height': item.height,
|
||||
'min-height': item.height,
|
||||
'max-height': item.height,
|
||||
'transform': f'skew({item.font.italic_angle}deg, 0deg)',
|
||||
'text-align': 'center',
|
||||
'display': 'flex',
|
||||
'flex-flow': 'row nowrap',
|
||||
'justify-content': 'space-between',
|
||||
# 'padding-left': item.font.leading
|
||||
}):
|
||||
for char in item:
|
||||
render(char)
|
||||
render(ltpage)
|
||||
|
||||
def close(self):
|
||||
|
||||
@@ -1,7 +1,10 @@
|
||||
import logging
|
||||
import re
|
||||
import json
|
||||
|
||||
from typing import Dict
|
||||
|
||||
from xml.sax import saxutils
|
||||
from contextlib import contextmanager
|
||||
|
||||
from ..layouts import LTPage
|
||||
@@ -28,8 +31,17 @@ def get_color(col: PDFGraphicStateColor):
|
||||
return f"cmyk({','.join(map(str, color_val))})"
|
||||
elif color_type == 'gray':
|
||||
return f'gray({color_val})'
|
||||
elif color_type == "custom":
|
||||
# Todo: convert these to more friendly color types
|
||||
return f"{col.custom['type']}({col.custom['defintion']})"
|
||||
return ""
|
||||
|
||||
FIRST_CAP_RE = re.compile('(.)([A-Z][a-z]+)')
|
||||
ALL_CAP_RE = re.compile('([a-z0-9])([A-Z])')
|
||||
def convert_capcase_to_snakecase(text: str) -> str:
|
||||
s1 = FIRST_CAP_RE.sub(r'\1-\2', text)
|
||||
return ALL_CAP_RE.sub(r'\1-\2', s1).lower()
|
||||
|
||||
class XMLConverter(PDFConverter):
|
||||
def __init__(self,
|
||||
rsrcmgr,
|
||||
@@ -71,7 +83,7 @@ class XMLConverter(PDFConverter):
|
||||
lineend = ''
|
||||
deep_space = ''
|
||||
attrs = " ".join([
|
||||
f'{name}="{value}"'
|
||||
f'{name}="{saxutils.escape(str(value))}"'
|
||||
for name, value in attr_dict.items()
|
||||
])
|
||||
self.write(f"<{tag_name} {attrs}>", lineend=lineend)
|
||||
@@ -82,7 +94,7 @@ class XMLConverter(PDFConverter):
|
||||
|
||||
def place_elm_close(self, tag_name: str, attr_dict: Dict[str, str] = {}, as_childless = True):
|
||||
attrs = " ".join([
|
||||
f'{name}="{value}"'
|
||||
f'{name}="{saxutils.escape(str(value))}"'
|
||||
for name, value in attr_dict.items()
|
||||
])
|
||||
if as_childless:
|
||||
@@ -113,22 +125,29 @@ class XMLConverter(PDFConverter):
|
||||
})
|
||||
|
||||
def place_text(self, char: LTChar):
|
||||
tag_name = 'char'
|
||||
if isinstance(char, LTCharBlock):
|
||||
tag_name = 'char-block'
|
||||
with self.place_elm_with_child('char', {
|
||||
'x0': char.x0,
|
||||
'x1': char.x1,
|
||||
'y0': char.y0,
|
||||
'y1': char.y1,
|
||||
}, no_additional_char=True):
|
||||
self.write(saxutils.escape(char.get_text()), lineend='', deep_space="")
|
||||
|
||||
def render_char_block(self, char_block: LTCharBlock):
|
||||
attr = {
|
||||
'size': char.size,
|
||||
"color": get_color(char.graphicstate.ncolor),
|
||||
"x0": char.x0,
|
||||
"x1": char.x1,
|
||||
"y0": char.y0,
|
||||
"y1": char.y1,
|
||||
'size': char_block.size,
|
||||
"color": get_color(char_block.graphicstate.ncolor),
|
||||
"x0": char_block.x0,
|
||||
"x1": char_block.x1,
|
||||
"y0": char_block.y0,
|
||||
"y1": char_block.y1,
|
||||
}
|
||||
for key, value in char.font.descriptor.items():
|
||||
for key, value in char_block.font.descriptor.items():
|
||||
if key != "Type" and "FontFile" not in key:
|
||||
attr["font-" + key] = value
|
||||
with self.place_elm_with_child(tag_name, attr, no_additional_char=True):
|
||||
self.write(char.get_text(), lineend='', deep_space="")
|
||||
attr[convert_capcase_to_snakecase(key)] = value
|
||||
with self.place_elm_with_child("char-block", attr):
|
||||
for char in char_block:
|
||||
self.place_text(char)
|
||||
|
||||
def render_curve(self, item: LTCurve):
|
||||
attr = {
|
||||
@@ -164,8 +183,8 @@ class XMLConverter(PDFConverter):
|
||||
render(child)
|
||||
elif isinstance(item, LTImage):
|
||||
self.place_image(item)
|
||||
elif isinstance(item, LTChar) or isinstance(item, LTCharBlock):
|
||||
self.place_text(item)
|
||||
elif isinstance(item, LTCharBlock):
|
||||
self.render_char_block(item)
|
||||
render(ltpage)
|
||||
|
||||
def close(self):
|
||||
|
||||
@@ -531,6 +531,19 @@ class PDFFont(object):
|
||||
@abstractmethod
|
||||
def to_unichr(self, cid):
|
||||
raise NotImplementedError
|
||||
|
||||
@property
|
||||
def font_weight(self):
|
||||
if 'FontWeight' in self.descriptor.keys():
|
||||
return self.descriptor['FontWeight']
|
||||
elif 'bold' in self.fontname.lower():
|
||||
return 'bold'
|
||||
else:
|
||||
return None
|
||||
|
||||
@property
|
||||
def is_bold(self):
|
||||
return self.font_weight == 'bold' or self.font_weight > 549
|
||||
|
||||
|
||||
# PDFSimpleFont
|
||||
|
||||
@@ -5,6 +5,7 @@ class PDFGraphicStateColor:
|
||||
self.__rgb = None
|
||||
self.__gray = None
|
||||
self.__cmyk = None
|
||||
self.__custom = None
|
||||
|
||||
def get_color(self):
|
||||
if self.__rgb is not None:
|
||||
@@ -13,6 +14,8 @@ class PDFGraphicStateColor:
|
||||
return 'cmyk', self.cmyk
|
||||
elif self.__gray is not None:
|
||||
return 'gray', self.gray
|
||||
elif self.__custom is not None:
|
||||
return 'custom', self.custom
|
||||
else: return None, None
|
||||
|
||||
@property
|
||||
@@ -34,6 +37,11 @@ class PDFGraphicStateColor:
|
||||
if self.__gray is not None: return float(self.__gray)
|
||||
else: raise self.NotSet
|
||||
|
||||
@property
|
||||
def custom(self):
|
||||
if self.__custom is not None: return dict(self.__custom)
|
||||
else: raise self.NotSet
|
||||
|
||||
@rgb.setter
|
||||
def rgb(self, rgb):
|
||||
self.__rgb = rgb
|
||||
@@ -46,11 +54,16 @@ class PDFGraphicStateColor:
|
||||
def gray(self, color):
|
||||
self.__gray = color
|
||||
|
||||
@custom.setter
|
||||
def custom(self, color):
|
||||
self.__custom = color
|
||||
|
||||
def copy(self):
|
||||
cp = self.__class__()
|
||||
cp.gray = self.__gray
|
||||
cp.rgb = self.__rgb
|
||||
cp.cmyk = self.__cmyk
|
||||
cp.custom = self.__custom
|
||||
return cp
|
||||
|
||||
def __repr__(self):
|
||||
@@ -58,4 +71,5 @@ class PDFGraphicStateColor:
|
||||
if self.__gray is not None: rep += f' gray={self.__gray}'
|
||||
if self.__rgb is not None: rep += f' rgb=[{",".join(map(str, self.__rgb))}]'
|
||||
if self.__cmyk is not None: rep += f' cmyk=[{",".join(map(str, self.__cmyk))}]'
|
||||
if self.__custom is not None: rep += f' custom={self.__custom}'
|
||||
return rep + '/>'
|
||||
@@ -1,6 +1,7 @@
|
||||
import logging
|
||||
import operator
|
||||
|
||||
from collections import OrderedDict
|
||||
from typing import List
|
||||
|
||||
|
||||
@@ -26,7 +27,7 @@ from .PDFGraphicState import PDFGraphicState
|
||||
from .PDFTextState import PDFTextState
|
||||
from .PDFContentParser import PDFContentParser
|
||||
|
||||
from ..utils import settings, mult_matrix, MATRIX_IDENTITY
|
||||
from ..utils import mult_matrix, MATRIX_IDENTITY
|
||||
from .constants import LITERAL_FORM, LITERAL_IMAGE
|
||||
from .types import CurvePoint, CurvePath
|
||||
|
||||
@@ -54,7 +55,7 @@ class PDFPageInterpreter(object):
|
||||
self.resources = resources
|
||||
self.fontmap = {}
|
||||
self.xobjmap = {}
|
||||
self.csmap = PREDEFINED_COLORSPACE.copy()
|
||||
self.csmap:OrderedDict = PREDEFINED_COLORSPACE.copy()
|
||||
if not resources:
|
||||
return
|
||||
|
||||
@@ -303,8 +304,7 @@ class PDFPageInterpreter(object):
|
||||
try:
|
||||
self.scs = self.csmap[literal_name(name)]
|
||||
except KeyError:
|
||||
if settings.STRICT:
|
||||
raise PDFInterpreterError('Undefined ColorSpace: %r' % name)
|
||||
raise PDFInterpreterError('Undefined ColorSpace: %r' % name)
|
||||
return
|
||||
|
||||
# setcolorspace-non-strokine
|
||||
@@ -312,8 +312,7 @@ class PDFPageInterpreter(object):
|
||||
try:
|
||||
self.ncs = self.csmap[literal_name(name)]
|
||||
except KeyError:
|
||||
if settings.STRICT:
|
||||
raise PDFInterpreterError('Undefined ColorSpace: %r' % name)
|
||||
raise PDFInterpreterError('Undefined ColorSpace: %r' % name)
|
||||
return
|
||||
|
||||
# setgray-stroking
|
||||
@@ -352,25 +351,74 @@ class PDFPageInterpreter(object):
|
||||
#self.do_cs(LITERAL_DEVICE_CMYK)
|
||||
return
|
||||
|
||||
# setcolor
|
||||
def do_SCN(self):
|
||||
if self.scs:
|
||||
n = self.scs.ncomponents
|
||||
else:
|
||||
if settings.STRICT:
|
||||
raise PDFInterpreterError('No colorspace specified!')
|
||||
n = 1
|
||||
self.pop(n)
|
||||
return
|
||||
def __process_ICCBased(self, n: int, components: list):
|
||||
if n == 1:
|
||||
return {
|
||||
"type": "gray",
|
||||
"definition": components
|
||||
}
|
||||
elif n == 3:
|
||||
return {
|
||||
"type": "rgb",
|
||||
"definition": components
|
||||
}
|
||||
elif n == 4:
|
||||
return {
|
||||
"type": "cmyk",
|
||||
"definition": components
|
||||
}
|
||||
raise PDFInterpreterError("Unsupported ICCBased color")
|
||||
|
||||
def do_scn(self):
|
||||
# setcolor
|
||||
def __process_scn(self):
|
||||
if self.ncs:
|
||||
n = self.ncs.ncomponents
|
||||
else:
|
||||
if settings.STRICT:
|
||||
raise PDFInterpreterError('No colorspace specified!')
|
||||
n = 1
|
||||
self.pop(n)
|
||||
raise PDFInterpreterError('No colorspace specified!')
|
||||
components = self.pop(n)
|
||||
obj_id = components[0]
|
||||
if self.ncs.name == "ICCBased":
|
||||
return self.__process_ICCBased(n, components)
|
||||
if self.ncs.name not in self.resources.keys():
|
||||
log.warning("Color space not in resources")
|
||||
return {
|
||||
"type": self.ncs.name,
|
||||
"defintion": f"{n}|({','.join(map(str, components))})"
|
||||
}
|
||||
if obj_id.name not in self.resources[self.ncs.name].keys():
|
||||
raise PDFInterpreterError("Invalid Color reference")
|
||||
|
||||
color_data = self.resources[self.ncs.name][obj_id.name].resolve()
|
||||
|
||||
if isinstance(color_data, PDFStream):
|
||||
color_data = color_data.attrs
|
||||
|
||||
return {
|
||||
"type": self.ncs.name,
|
||||
"defintion": color_data
|
||||
}
|
||||
def do_SCN(self):
|
||||
processed_col = self.__process_scn()
|
||||
if processed_col['type'] == 'rgb':
|
||||
self.graphicstate.scolor.rgb = processed_col['definition']
|
||||
elif processed_col['type'] == 'gray':
|
||||
self.graphicstate.scolor.gray = processed_col['definition'][0]
|
||||
elif processed_col['type'] == 'cmyk':
|
||||
self.graphicstate.scolor.cmyk = processed_col['definition']
|
||||
else:
|
||||
self.graphicstate.scolor.custom = processed_col
|
||||
return
|
||||
|
||||
def do_scn(self):
|
||||
processed_col = self.__process_scn()
|
||||
if processed_col['type'] == 'rgb':
|
||||
self.graphicstate.ncolor.rgb = processed_col['definition']
|
||||
elif processed_col['type'] == 'gray':
|
||||
self.graphicstate.ncolor.gray = processed_col['definition'][0]
|
||||
elif processed_col['type'] == 'cmyk':
|
||||
self.graphicstate.ncolor.cmyk = processed_col['definition']
|
||||
else:
|
||||
self.graphicstate.ncolor.custom = processed_col
|
||||
return
|
||||
|
||||
def do_SC(self):
|
||||
@@ -432,6 +480,8 @@ class PDFPageInterpreter(object):
|
||||
def do_Tw(self, space):
|
||||
self.textstate.wordspace = space
|
||||
return
|
||||
|
||||
# def do_Th(self, )
|
||||
|
||||
# textscale
|
||||
def do_Tz(self, scale):
|
||||
@@ -448,9 +498,8 @@ class PDFPageInterpreter(object):
|
||||
try:
|
||||
self.textstate.font = self.fontmap[literal_name(fontid)]
|
||||
except KeyError:
|
||||
if settings.STRICT:
|
||||
raise PDFInterpreterError('Undefined Font id: %r' % fontid)
|
||||
self.textstate.font = self.rsrcmgr.get_font(None, {})
|
||||
raise PDFInterpreterError('Undefined Font id: %r' % fontid)
|
||||
# self.textstate.font = self.rsrcmgr.get_font(None, {})
|
||||
self.textstate.fontsize = fontsize
|
||||
return
|
||||
|
||||
@@ -495,9 +544,7 @@ class PDFPageInterpreter(object):
|
||||
# show-pos
|
||||
def do_TJ(self, seq: bytearray):
|
||||
if self.textstate.font is None:
|
||||
if settings.STRICT:
|
||||
raise PDFInterpreterError('No font specified!')
|
||||
return
|
||||
raise PDFInterpreterError('No font specified!')
|
||||
self.device.render_string(self.textstate.copy(), seq, self.ncs, self.graphicstate.copy())
|
||||
return
|
||||
|
||||
@@ -540,9 +587,7 @@ class PDFPageInterpreter(object):
|
||||
try:
|
||||
xobj = PDFStream.validated_stream(self.xobjmap[xobjid])
|
||||
except KeyError:
|
||||
if settings.STRICT:
|
||||
raise PDFInterpreterError('Undefined xobject id: %r' % xobjid)
|
||||
return
|
||||
raise PDFInterpreterError('Undefined xobject id: %r' % xobjid)
|
||||
log.info('Processing xobj: %r', xobj)
|
||||
subtype = xobj.get('Subtype')
|
||||
if subtype is LITERAL_FORM and 'BBox' in xobj:
|
||||
@@ -618,8 +663,7 @@ class PDFPageInterpreter(object):
|
||||
log.debug('exec: %s', name)
|
||||
func()
|
||||
else:
|
||||
if settings.STRICT:
|
||||
raise PDFInterpreterError('Unknown operator: %r' % name)
|
||||
raise PDFInterpreterError('Unknown operator: %r' % name)
|
||||
else:
|
||||
self.push(obj)
|
||||
return
|
||||
@@ -12,7 +12,7 @@ from .exceptions import * # pylint: disable=W0614
|
||||
##
|
||||
class PDFObjRef(PDFObject):
|
||||
|
||||
def __init__(self, doc, objid, _):
|
||||
def __init__(self, doc, objid, a):
|
||||
if objid == 0:
|
||||
if settings.STRICT:
|
||||
raise PDFValueError('PDF object id cannot be 0.')
|
||||
|
||||
@@ -100,7 +100,6 @@ class PSBaseParser(object):
|
||||
linebuf += self.buf[self.charpos:]
|
||||
self.charpos = len(self.buf)
|
||||
log.debug('nextline: %r, %r', linepos, linebuf)
|
||||
|
||||
return (linepos, linebuf)
|
||||
|
||||
def revreadlines(self):
|
||||
|
||||
@@ -60,6 +60,9 @@ class LTCharBlock(LTComponent):
|
||||
def __repr__(self):
|
||||
return f"""<{self.__class__.__name__} font="{self.fontname}" text="{self.get_text()}"/>"""
|
||||
|
||||
def __iter__(self):
|
||||
return iter(self.chars)
|
||||
|
||||
def get_text(self):
|
||||
return "".join([ c.get_text() for c in self.chars ])
|
||||
|
||||
|
||||
+11
-10
@@ -3,35 +3,36 @@ import os
|
||||
|
||||
from typing import List
|
||||
from pdfmajor.converters import convert_file
|
||||
from xml.etree import ElementTree
|
||||
|
||||
def rel_path(*arg: List[str]) -> str:
|
||||
return os.path.join(os.path.dirname(__file__), *arg)
|
||||
|
||||
EXT = 'xml'
|
||||
EXT = 'html'
|
||||
INPUT_FOLDER = rel_path("./pdf")
|
||||
OUTPUT_FOLDER = rel_path(f"./output/{EXT}")
|
||||
|
||||
if not os.path.exists(OUTPUT_FOLDER):
|
||||
os.makedirs(OUTPUT_FOLDER)
|
||||
|
||||
# files = os.listdir(INPUT_FOLDER)
|
||||
# files = ['fonts.pdf']
|
||||
# files = ['bar-charts.pdf']
|
||||
# files = ['font-color.pdf']
|
||||
files = ['tables.pdf']
|
||||
files = os.listdir(INPUT_FOLDER)
|
||||
|
||||
TOTAL = len(files)
|
||||
for idx, file_name in enumerate(files):
|
||||
file_name_no_ext = re.sub(r'\.pdf$',"", file_name)
|
||||
input_file_path = os.path.join(INPUT_FOLDER, file_name)
|
||||
output_file_path = os.path.join(OUTPUT_FOLDER, file_name_no_ext + "." + EXT)
|
||||
|
||||
print(f"processing {file_name} {idx}/{TOTAL}")
|
||||
if len(file_name) > len(file_name_no_ext):
|
||||
with open(os.path.join(INPUT_FOLDER, file_name), 'rb') as input_file:
|
||||
with open(os.path.join(OUTPUT_FOLDER, file_name_no_ext + "." + EXT), 'wb') as output_file:
|
||||
print(f"processing {file_name} {idx}/{TOTAL}")
|
||||
with open(input_file_path, 'rb') as input_file:
|
||||
with open(output_file_path, 'wb') as output_file:
|
||||
convert_file(
|
||||
input_file=input_file,
|
||||
output_file=output_file,
|
||||
out_type=EXT,
|
||||
debug=True,
|
||||
)
|
||||
print(f"processing {idx+1}/{TOTAL}")
|
||||
print(f" > testing format {file_name} {idx}/{TOTAL}")
|
||||
ElementTree.parse(output_file_path)
|
||||
print(f"processing {idx+1}/{TOTAL}")
|
||||
@@ -10,7 +10,7 @@ import sys
|
||||
with open('README.md') as readme_file:
|
||||
SETUP = {
|
||||
"name": "pdfmajor",
|
||||
"version": "1.1.1",
|
||||
"version": "1.1.10",
|
||||
"packages": find_packages(include=['pdfmajor*']),
|
||||
"install_requires": [
|
||||
'pycryptodome',
|
||||
@@ -46,8 +46,9 @@ with open('README.md') as readme_file:
|
||||
# ==============
|
||||
# Update __init__.py
|
||||
# ==============
|
||||
from bin.recreate_init import update_pdfmajor__init___
|
||||
from bin.recreate_init import update_pdfmajor__init___, update_current_version_lock
|
||||
update_pdfmajor__init___(SETUP["version"], SETUP["long_description"])
|
||||
update_current_version_lock(SETUP["version"])
|
||||
|
||||
# ==============
|
||||
# Run Setup
|
||||
|
||||
Reference in new issue
Block a user