17 Commits
Author SHA1 Message Date
ari 924596e38d - added consistency to PDFGraphicStateCol 2018-11-29 15:39:16 -05:00
ari 2ea0b717f9 - added better logging options
- added test case for bad chars
2018-11-23 14:44:09 -05:00
ari 38f8ca76a6 - better loggin system
- adde test case for bad characters
2018-11-23 14:43:51 -05:00
ari ac49ad1bcf - sanitizing the xml chars 2018-11-21 09:19:33 -05:00
ari d74bf1eaa9 - added support for ICCSBAsed colors 2018-11-09 10:24:04 -05:00
ari cf3c89bf25 supporting ICCSBased colors 2018-11-09 10:22:44 -05:00
ari b491cd2181 - v1.1.8 2018-11-08 14:53:28 -05:00
ari 70144c8fe1 - updated docx
- sanitizing xml attributes
2018-11-04 16:28:29 -05:00
ari 0d832bf7fa version inc 2018-10-31 14:45:37 -04:00
ari 7319b7f584 xml chars output bbx instead of width/height 2018-10-31 14:45:02 -04:00
ari 5b641d6243 comment out leading for now 2018-10-29 16:35:32 -04:00
ari 10d679d379 clean up 2018-10-29 16:26:57 -04:00
ari 5378a4f34c - better color grabbing for scn
- show custom type in converters
2018-10-29 16:25:50 -04:00
ari 42cbc8e39e - using snake case
- not outputting is_bold
2018-10-29 13:18:12 -04:00
ari 66004988f4 actually cleaning it all prior to deployment 2018-10-29 13:04:32 -04:00
ari 7722b99f70 Deployong new version - v1.1.4 2018-10-29 13:03:28 -04:00
ari 66b5fea65c - compatible xml-converter with char-blocks
- consitent attr naming convention for fonts
2018-10-29 13:03:11 -04:00
24 changed files with 308 additions and 141 deletions

No files matched your search

+1 -1
View File
@@ -1 +1 @@
v1.1.3
v1.1.12
+12 -1
View File
@@ -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.
+2 -2
View File
@@ -4,12 +4,12 @@ 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 -m "Deployong new version - $(cat .version)"
git commit
git push
git tag $(cat .version)
+12 -1
View File
@@ -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
View File
@@ -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
View File
@@ -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
View File
@@ -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
View File
@@ -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, 3)
__version__ = (1, 1, 12)
if __name__ == '__main__':
print(
+32 -33
View File
@@ -25,7 +25,10 @@ def get_color(col: PDFGraphicStateColor):
elif color_type == 'cmyk':
return f"cmyk({','.join(map(str, color_val))})"
elif color_type == 'gray':
return f'rgba(0,0,0,{1-color_val})'
return f'rgba(0,0,0,{1-color_val[0]})'
elif color_type == "custom":
# Todo: convert these to more friendly color types
return f"custom({col.custom['type']})"
return "none"
class HTMLConverter(PDFConverter):
@@ -131,6 +134,8 @@ class HTMLConverter(PDFConverter):
'position': 'absolute',
'left': f'{item.x0}px',
'bottom': f'{item.y0}px',
'width': f'{item.width}px',
'height': f'{item.height}px',
}
path = ""
svg_attr = {
@@ -138,42 +143,36 @@ class HTMLConverter(PDFConverter):
'z-index': 2
}
if item.height > 0:
dy = 1.0/item.height
dx = (item.width/item.height)/(item.x1-item.x0)
svg_attr.update({
"viewBox": "0 0 %s %s" % ( item.width/item.height, 1 )
})
else:
dx = 1.0/(item.x1-item.x0)
dy = 1.0
svg_attr.update({
"viewBox": "0 0 1 1"
})
p_vals = { "x": [], "y": [] }
if item.height > 1:
svg_attr.update({
'height': f'{item.height}px',
})
else:
svg_attr.update({
'height': '1px',
})
if item.width > 1:
svg_attr.update({
'width': f'{item.width}px',
})
else:
svg_attr.update({
'width': '1px',
})
for p in item.paths:
for pt in p.points:
p_vals['x'].append(pt.x)
p_vals['y'].append(pt.y)
mx_x = max([*p_vals['x'], 1])
mn_x = min([*p_vals['x'], 0])
mx_y = max([*p_vals['y'], 1])
mn_y = min([*p_vals['y'], 0])
if mx_x == mn_x:
mn_x -= 1
if mx_y == mn_y:
mn_y -= 1
dx = 1/( mx_x - mn_x )
dy = (item.height/item.width)/( mx_y - mn_y )
ROUND_VAL = 5
svg_attr.update({
# "viewBox": f"{min(p_vals['x'])} {min(p_vals['y'])} {max(p_vals['x'])} {max(p_vals['y'])}",
"viewBox": f"{round(mn_x*dx, ROUND_VAL)} {round(mn_y*dy, ROUND_VAL)} {round(mx_x*dx , ROUND_VAL)} {round(mx_y*dy, ROUND_VAL)}",
})
for p in item.paths:
if p.method == CurvePath.METHOD.MOVE_TO:
path += f'M{" ".join( f"{(item.width - (p.x-item.x0) )*dx} {(item.height- (p.y-item.y0) )*dy}" for p in p.points )} '
path += f'M{" ".join( f"{round(dx*pt.x, ROUND_VAL)} {round(dy*pt.y, ROUND_VAL)}" for pt in p.points )} '
if p.method == CurvePath.METHOD.LINE_TO:
path += f'L{" ".join( f"{(item.width - (p.x-item.x0) )*dx} {( item.height - (p.y-item.y0) )*dy}" for p in p.points )} '
path += f'L{" ".join( f"{round(dx*pt.x, ROUND_VAL)} {round(dy*pt.y, ROUND_VAL)}" for pt in p.points )} '
if p.method == CurvePath.METHOD.CLOSE_PATH:
path += 'Z'
with self.place_elm_with_child('svg', svg_attr, css):
@@ -236,7 +235,7 @@ class HTMLConverter(PDFConverter):
'display': 'flex',
'flex-flow': 'row nowrap',
'justify-content': 'space-between',
'padding-left': item.font.leading
# 'padding-left': item.font.leading
}):
for char in item:
render(char)
+12 -8
View File
@@ -1,17 +1,19 @@
import logging
import re
import os
from typing import List
from io import BytesIO, StringIO, TextIOWrapper
from tqdm import tqdm
from ..layouts import PDFLayoutAnalyzer
from ..interpreter.PDFResourceManager import PDFResourceManager
from ..interpreter.PDFPage import PDFPage
from ..interpreter.PDFPageInterpreter import PDFPageInterpreter
from ..imagewriter import ImageWriter
from ..utils import set_log_level, get_logger, logging
log = logging.getLogger(__name__)
log = get_logger(__name__)
## PDFConverter
##
@@ -29,11 +31,10 @@ class PDFConverter(PDFLayoutAnalyzer):
check_extractable: bool = True,
pagenos: List[int] = None,
dont_export_images: bool = False,
debug: bool = False,
debug_level: int = logging.WARNING,
) -> TextIOWrapper:
if debug:
log.setLevel(logging.DEBUG)
set_log_level(debug_level)
if dont_export_images:
image_folder_path = None
@@ -53,9 +54,12 @@ class PDFConverter(PDFLayoutAnalyzer):
interpreter = PDFPageInterpreter(rsrcmgr, device)
log.debug("Reading pages....")
pages = PDFPage.get_pages(input_file, pagenos=pagenos, maxpages=maxpages, password=password, caching=caching, check_extractable=check_extractable)
for idx, page in enumerate(pages):
log.debug(f"Reading page #{idx}")
interpreter.process_page(page)
page_waiter = tqdm(enumerate(pages), disable=debug_level > logging.INFO)
for _, page in page_waiter:
page_waiter.set_description("Processing pdf...")
interpreter.process_page(page)
page_waiter.close()
device.close()
return output_file
+36 -17
View File
@@ -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):
+47 -41
View File
@@ -8,6 +8,7 @@ from .HTMLConverter import HTMLConverter
from .JSONConverter import JSONConverter
from .XMLConverter import XMLConverter
from .TextConverter import TextConverter
from ..utils import logging
def convert_file(
input_file: io.TextIOWrapper,
@@ -19,7 +20,8 @@ def convert_file(
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
debug: bool = False,
dont_export_images: bool = False,
debug_level: int = logging.WARNING,
out_type: str = 'html',
):
if output_file is None:
@@ -36,54 +38,58 @@ def convert_file(
raise Exception("Please make sure that the file name and output type match!")
if out_type == 'html':
return HTMLConverter.parse_file(
input_file,
output_file,
image_folder_path,
codec,
maxpages,
password,
caching,
check_extractable,
pagenos,
debug,
input_file=input_file,
output_file=output_file,
image_folder_path=image_folder_path,
codec=codec,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=check_extractable,
pagenos=pagenos,
dont_export_images=dont_export_images,
debug_level=debug_level,
)
elif out_type == 'xml':
return XMLConverter.parse_file(
input_file,
output_file,
image_folder_path,
codec,
maxpages,
password,
caching,
check_extractable,
pagenos,
debug,
input_file=input_file,
output_file=output_file,
image_folder_path=image_folder_path,
codec=codec,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=check_extractable,
pagenos=pagenos,
dont_export_images=dont_export_images,
debug_level=debug_level,
)
elif out_type == 'json':
return JSONConverter.parse_file(
input_file,
output_file,
image_folder_path,
codec,
maxpages,
password,
caching,
check_extractable,
pagenos,
debug,
input_file=input_file,
output_file=output_file,
image_folder_path=image_folder_path,
codec=codec,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=check_extractable,
pagenos=pagenos,
dont_export_images=dont_export_images,
debug_level=debug_level,
)
elif out_type == 'text':
return TextConverter.parse_file(
input_file,
output_file,
image_folder_path,
codec,
maxpages,
password,
caching,
check_extractable,
pagenos,
debug,
input_file=input_file,
output_file=output_file,
image_folder_path=image_folder_path,
codec=codec,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=check_extractable,
pagenos=pagenos,
dont_export_images=dont_export_images,
debug_level=debug_level,
)
else: raise Exception("Please specify out_type as 'html' or 'xml' or 'json' or 'text'")
@@ -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
@@ -31,7 +34,12 @@ class PDFGraphicStateColor:
@property
def gray(self):
if self.__gray is not None: return float(self.__gray)
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
@@ -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 + '/>'
+4 -2
View File
@@ -7,7 +7,9 @@ from .PDFStream import resolve1, int_value, list_value, dict_value
from .PDFParser import PDFParser
from .PDFDocument import PDFDocument, PDFTextExtractionNotAllowed
log = logging.getLogger(__name__)
from ..utils import get_logger
log = get_logger(__name__)
# some predefined literals and keywords.
LITERAL_PAGE = LIT('Page')
@@ -89,7 +91,7 @@ class PDFPage(object):
tree_type = tree.get('type')
if tree_type is LITERAL_PAGES and 'Kids' in tree:
log.info('Pages: Kids=%r', tree['Kids'])
# log.info('Pages: Kids=%r', tree['Kids'])
for c in list_value(tree['Kids']):
for x in search(c, tree):
yield x
+65 -11
View File
@@ -1,6 +1,7 @@
import logging
import operator
from collections import OrderedDict
from typing import List
@@ -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
@@ -350,21 +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:
raise PDFInterpreterError('No colorspace specified!')
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:
raise PDFInterpreterError('No colorspace specified!')
self.pop(n)
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):
+1 -1
View File
@@ -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):
+2 -1
View File
@@ -9,4 +9,5 @@ from .generic import *
from .lzw import *
from .matrix import *
from .text import *
from .types import *
from .types import *
from .log import *
+17
View File
@@ -0,0 +1,17 @@
import logging
logging.basicConfig(
level=logging.WARNING
)
LOGGERS = {}
def set_log_level(debug_level: int):
logging.basicConfig(level=debug_level)
for _, logger in LOGGERS.items():
logger.setLevel(debug_level)
def get_logger(logger_name: str) -> logging.Logger:
if logger_name not in LOGGERS.keys():
LOGGERS[logger_name] = logging.getLogger(logger_name)
return LOGGERS[logger_name]
Regular → Executable
+19 -11
View File
@@ -1,8 +1,12 @@
#!/usr/bin/env python
import re
import os
import logging
from typing import List
from pdfmajor.converters import convert_file
from xml.etree import ElementTree
from tqdm import tqdm
def rel_path(*arg: List[str]) -> str:
return os.path.join(os.path.dirname(__file__), *arg)
@@ -14,24 +18,28 @@ 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):
waiter = tqdm(enumerate(files), total=TOTAL)
for idx, file_name in waiter:
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:
waiter.set_description(f"Processing {file_name}")
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,
debug_level=logging.NOTSET,
)
print(f"processing {idx+1}/{TOTAL}")
if EXT == 'xml':
waiter.set_description(f" > testing format {file_name}")
ElementTree.parse(output_file_path)
waiter.refresh()
waiter.set_description("Done")
waiter.close()
Binary file not shown.
Binary file not shown.
+1 -1
View File
@@ -10,7 +10,7 @@ import sys
with open('README.md') as readme_file:
SETUP = {
"name": "pdfmajor",
"version": "1.1.3",
"version": "1.1.12",
"packages": find_packages(include=['pdfmajor*']),
"install_requires": [
'pycryptodome',