9 Commits
Author SHA1 Message Date
ari ac2c462561 - improved html converter 2019-01-22 13:16:46 -05:00
ari 19712f1f0f cleaner html converter 2019-01-22 13:16:17 -05:00
ari ec02a7d38b - yaml converter
- adjusting curve detection
2019-01-16 16:56:14 -05:00
ari 0345ca01ba - slightly more accurate shape detection 2019-01-16 16:55:30 -05:00
ari b36f6bc907 silencing the unknown operator warning 2019-01-16 12:08:15 -05:00
ari f9f9a59793 - added yaml converter 2019-01-16 12:08:03 -05:00
ari b7026793d7 - minor bug fix -- xobj invalid name 2019-01-13 13:13:37 -05:00
ari addd59ed0f updated readme 2019-01-11 15:25:03 -05:00
ari d43b617309 - new doc build 2019-01-11 15:23:15 -05:00
21 changed files with 542 additions and 137 deletions

No files matched your search

+1 -1
View File
@@ -1 +1 @@
v1.3.2b v1.3.5
+1 -1
View File
@@ -19,7 +19,7 @@ See documentation [here](https://asosnovsky.github.io/pdfmajor/).
## Basic Example ## Basic Example
```py ```py
from pdfmajor.interpreter import PageInterpreter from pdfmajor.interpreter import PDFInterpreter
for page in PDFInterpreter("/path/to/pdf.pdf"): for page in PDFInterpreter("/path/to/pdf.pdf"):
print("page start", page.page_num) print("page start", page.page_num)
+1 -1
View File
@@ -121,7 +121,7 @@
<h2 id="interpreter">interpreter</h2> <h2 id="interpreter">interpreter</h2>
<p>a interpreter of the pdf-standard commands</p> <p>a interpreter of the pdf-standard commands</p>
<h3 id="example">Example</h3> <h3 id="example">Example</h3>
<pre><code class="py">from pdfmajor.interpreter import PageInterpreter <pre><code class="py">from pdfmajor.interpreter import PDFInterpreter
for page in PDFInterpreter(&quot;/path/to/pdf.pdf&quot;): for page in PDFInterpreter(&quot;/path/to/pdf.pdf&quot;):
print(&quot;page start&quot;, page.page_num) print(&quot;page start&quot;, page.page_num)
+2 -2
View File
@@ -128,7 +128,7 @@
<h2 id="documentation">Documentation</h2> <h2 id="documentation">Documentation</h2>
<p>See documentation <a href="https://asosnovsky.github.io/pdfmajor/">here</a>.</p> <p>See documentation <a href="https://asosnovsky.github.io/pdfmajor/">here</a>.</p>
<h2 id="basic-example">Basic Example</h2> <h2 id="basic-example">Basic Example</h2>
<pre><code class="py">from pdfmajor.interpreter import PageInterpreter <pre><code class="py">from pdfmajor.interpreter import PDFInterpreter
for page in PDFInterpreter(&quot;/path/to/pdf.pdf&quot;): for page in PDFInterpreter(&quot;/path/to/pdf.pdf&quot;):
print(&quot;page start&quot;, page.page_num) print(&quot;page start&quot;, page.page_num)
@@ -240,5 +240,5 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.</p>
<!-- <!--
MkDocs version : 1.0.4 MkDocs version : 1.0.4
Build Date UTC : 2018-12-24 06:52:28 Build Date UTC : 2019-01-11 20:22:59
--> -->
+1 -1
View File
@@ -1 +1 @@
{"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. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon. Documentation See documentation here . Basic Example from pdfmajor.interpreter import PageInterpreter for page in PDFInterpreter(\"/path/to/pdf.pdf\"): print(\"page start\", page.page_num) for item in page: print(\" >\", item) print(\"page end\", page.page_num) 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. However, after attempting to build and extend upon PDFMiner.six I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports. Features Functional extraction method based on generators Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) Font-Color extraction Shape fill and stroke color extraction CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. 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 running your own implementation of it on the pdfmajor.interpreter.PageInterpreter 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. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon.","title":"PDFMajor"},{"location":"#documentation","text":"See documentation here .","title":"Documentation"},{"location":"#basic-example","text":"from pdfmajor.interpreter import PageInterpreter for page in PDFInterpreter(\"/path/to/pdf.pdf\"): print(\"page start\", page.page_num) for item in page: print(\" >\", item) print(\"page end\", page.page_num)","title":"Basic Example"},{"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. However, after attempting to build and extend upon PDFMiner.six I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports.","title":"Why Another Fork?"},{"location":"#features","text":"Functional extraction method based on generators Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) Font-Color extraction Shape fill and stroke color extraction CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Note : We took out the layout-analysis process in this version (there is no more LTTLine 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. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon. Documentation See documentation here . Basic Example from pdfmajor.interpreter import PDFInterpreter for page in PDFInterpreter(\"/path/to/pdf.pdf\"): print(\"page start\", page.page_num) for item in page: print(\" >\", item) print(\"page end\", page.page_num) 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. However, after attempting to build and extend upon PDFMiner.six I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports. Features Functional extraction method based on generators Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) Font-Color extraction Shape fill and stroke color extraction CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. 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 running your own implementation of it on the pdfmajor.interpreter.PageInterpreter 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. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon.","title":"PDFMajor"},{"location":"#documentation","text":"See documentation here .","title":"Documentation"},{"location":"#basic-example","text":"from pdfmajor.interpreter import PDFInterpreter for page in PDFInterpreter(\"/path/to/pdf.pdf\"): print(\"page start\", page.page_num) for item in page: print(\" >\", item) print(\"page end\", page.page_num)","title":"Basic Example"},{"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. However, after attempting to build and extend upon PDFMiner.six I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports.","title":"Why Another Fork?"},{"location":"#features","text":"Functional extraction method based on generators Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) Font-Color extraction Shape fill and stroke color extraction CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Note : We took out the layout-analysis process in this version (there is no more LTTexLine truncated
+2 -2
View File
@@ -2,12 +2,12 @@
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url> <url>
<loc>None</loc> <loc>None</loc>
<lastmod>2018-12-24</lastmod> <lastmod>2019-01-11</lastmod>
<changefreq>daily</changefreq> <changefreq>daily</changefreq>
</url> </url>
<url> <url>
<loc>None</loc> <loc>None</loc>
<lastmod>2018-12-24</lastmod> <lastmod>2019-01-11</lastmod>
<changefreq>daily</changefreq> <changefreq>daily</changefreq>
</url> </url>
</urlset> </urlset>
Binary file not shown.
+2 -2
View File
@@ -24,7 +24,7 @@ See documentation [here](https://asosnovsky.github.io/pdfmajor/).
## Basic Example ## Basic Example
```py ```py
from pdfmajor.interpreter import PageInterpreter from pdfmajor.interpreter import PDFInterpreter
for page in PDFInterpreter("/path/to/pdf.pdf"): for page in PDFInterpreter("/path/to/pdf.pdf"):
print("page start", page.page_num) print("page start", page.page_num)
@@ -97,7 +97,7 @@ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
""" """
__version__ = (1, 3, 2b) __version__ = (1, 3, 5)
if __name__ == '__main__': if __name__ == '__main__':
print( print(
+18 -3
View File
@@ -8,6 +8,7 @@ from .html import convert_to_html
from .xml import convert_to_xml from .xml import convert_to_xml
from .json import convert_to_json from .json import convert_to_json
from .text import convert_to_text from .text import convert_to_text
from .yaml import convert_to_yaml
from ..utils import logging from ..utils import logging
def convert_file( def convert_file(
@@ -26,9 +27,9 @@ def convert_file(
): ):
if output_file is None: if output_file is None:
output_file = os.path.join( output_file = os.path.join(
os.path.dirname(input_file.name), os.path.dirname(input_file),
os.path.basename( os.path.basename(
re.sub(r"\.\w+$", "."+out_type, input_file.name) re.sub(r"\.\w+$", "."+out_type, input_file)
) )
) )
if re.search(re.escape(out_type) + r'$', output_file ) is None: if re.search(re.escape(out_type) + r'$', output_file ) is None:
@@ -75,6 +76,20 @@ def convert_file(
dont_export_images=dont_export_images, dont_export_images=dont_export_images,
debug_level=debug_level, debug_level=debug_level,
) )
elif out_type == 'yaml' or out_type == 'yml':
return convert_to_yaml(
input_file_path=input_file,
output_file_path=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': elif out_type == 'text':
return convert_to_text( return convert_to_text(
input_file_path=input_file, input_file_path=input_file,
@@ -89,4 +104,4 @@ def convert_file(
dont_export_images=dont_export_images, dont_export_images=dont_export_images,
debug_level=debug_level, debug_level=debug_level,
) )
else: raise Exception("Please specify out_type as 'html' or 'xml' or 'json' or 'text'") else: raise Exception("Please specify out_type as 'html' or 'xml' or 'json' or 'text' or 'yaml'")
+127 -96
View File
@@ -5,6 +5,8 @@ from ..interpreter import LTImage, LTTextBlock, LTCharBlock, LTChar, LTCurve, LT
from ..interpreter.commands import LTItem from ..interpreter.commands import LTItem
from ..interpreter.commands.state import CurvePath, PDFColor from ..interpreter.commands.state import CurvePath, PDFColor
INF = (1<<31) - 1
def convert_to_html( def convert_to_html(
input_file_path: str, input_file_path: str,
output_file_path: str, output_file_path: str,
@@ -43,19 +45,21 @@ def convert_to_html(
render_page(html, page) render_page(html, page)
def render_page(html: HTMLMaker, ltpage: PageInterpreter): def render_page(html: HTMLMaker, ltpage: PageInterpreter):
def render(item: LTItem): def render(item: LTItem, block = True):
if isinstance(item, LTCurve): if isinstance(item, LTCurve):
render_curve(html, item) render_curve(html, ltpage, item)
elif isinstance(item, LTXObject): elif isinstance(item, LTXObject):
with html.elm('div', { "class": 'xobject' }, { with html.elm('div', { "class": 'xobject' }, {
'position': 'absolute', # 'position': 'absolute',
'left': f'{item.x0}px', 'left': f'{item.x0}px',
'right': f'{item.x1}px',
'bottom': f'{item.y0}px', 'bottom': f'{item.y0}px',
'top': f'{item.y1}px',
'width': f'{item.width}px', 'width': f'{item.width}px',
'height': f'{item.height}px', 'height': f'{item.height}px',
}): }):
for child in item: for child in item:
render(child) render(child, False)
elif isinstance(item, LTImage): elif isinstance(item, LTImage):
name = item.name name = item.name
# if html.imagewriter is not None: # if html.imagewriter is not None:
@@ -68,42 +72,42 @@ def render_page(html: HTMLMaker, ltpage: PageInterpreter):
}) })
elif isinstance(item, LTChar): elif isinstance(item, LTChar):
with html.elm('span', { 'class': 'char' }, { with html.elm('span', { 'class': 'char' }, {
'width': item.width, 'width': str(item.width) + "px",
'min-width': item.width, 'min-width': str(item.width) + "px",
'max-width': item.width, 'max-width': str(item.width) + "px",
'height': item.height, 'height': str(item.height) + "px",
'min-height': item.height, 'min-height': str(item.height) + "px",
'max-height': item.height, 'max-height': str(item.height) + "px",
}): }):
html.write(item.get_text()) html.write(item.get_text())
elif isinstance(item, LTTextBlock): elif isinstance(item, LTTextBlock):
for char in item: with html.elm('span', {'class': 'text-block'}):
render(char) for char in item:
render(char)
elif isinstance(item, LTCharBlock): elif isinstance(item, LTCharBlock):
with html.elm('span', {'class': 'char-block'}): with html.elm('span', { 'class': 'char-block' }, {
with html.elm('p', { 'class': 'text-block' }, { 'position': 'absolute',
'position': 'absolute', 'left': f'{item.x0}',
'left': f'{item.x0}', 'bottom': f'{item.y0}',
'bottom': f'{item.y0}', 'font-size': f'{item.size}px',
'font-size': f'{item.size}px', 'font-family': item.fontname,
'font-family': item.fontname, 'font-weight': item.font.font_weight,
'font-weight': item.font.font_weight, 'color': get_color(item.color, default="black"),
'color': get_color(item.color, default="black"), 'width': str(item.width) + "px",
'width': item.width, 'min-width': str(item.width) + "px",
'min-width': item.width, 'max-width': str(item.width) + "px",
'max-width': item.width, 'height': str(item.height) + "px",
'height': item.height, 'min-height': str(item.height) + "px",
'min-height': item.height, 'max-height': str(item.height) + "px",
'max-height': item.height, 'transform': f'skew({item.font.italic_angle}deg, 0deg)',
'transform': f'skew({item.font.italic_angle}deg, 0deg)', 'text-align': 'center',
'text-align': 'center', 'display': 'flex',
'display': 'flex', 'flex-flow': 'row nowrap',
'flex-flow': 'row nowrap', 'justify-content': 'space-between',
'justify-content': 'space-between', # 'padding-left': item.font.leading
# 'padding-left': item.font.leading }):
}): for char in item:
for char in item: render(char)
render(char)
with html.elm('div', { "class": 'page', "id": f"page-{ltpage.page_num}" }, { with html.elm('div', { "class": 'page', "id": f"page-{ltpage.page_num}" }, {
'width': f'{ltpage.width}px', 'width': f'{ltpage.width}px',
@@ -125,69 +129,96 @@ def get_color(col: PDFColor, default: str = ""):
else: else:
return default return default
def render_curve(html: HTMLMaker, item: LTCurve): def render_curve(html: HTMLMaker, ltpage: PageInterpreter, item: LTCurve):
css = { path, svg_attr = create_svg_path(item)
'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 = {
'class': 'curve',
'z-index': 2
}
path_css = {
} stroke_col = get_color(item.stroke)
fill_col = get_color(item.fill)
path_css = {}
if fill_col:
path_css['fill'] = fill_col
if stroke_col:
path_css['stroke'] = stroke_col
# Compute ViewBox with html.elm('svg', svg_attr, css={
p_vals = { "x": [], "y": [] } 'border': '1px solid black',
'position': 'absolute',
for p in item.paths: 'left': f'{item.x0}px',
for pt in p.points: 'bottom': f'{ltpage.height - item.y0}px',
p_vals['x'].append(pt.x) 'top': f'{ltpage.height - item.y1}px',
p_vals['y'].append(pt.y) 'right': f'{item.x1}px',
'width': f'{item.width}px',
mx_x = max([*p_vals['x'], 1]) 'height': f'{item.height}px',
mn_x = min([*p_vals['x'], 0]) }):
mx_y = max([*p_vals['y'], 1]) html.singleton('path', {
mn_y = min([*p_vals['y'], 0]) "d": path,
**path_css
if mx_x == mn_x: }, {
mn_x -= 1 **path_css
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)}",
}) })
# Compute shape def create_svg_path(item: LTCurve):
for p in item.paths: path = ""
if p.method == CurvePath.METHOD.MOVE_TO: svg_attr = {
path += f'M{" ".join( f"{round(dx*pt.x, ROUND_VAL)} {round(dy*pt.y, ROUND_VAL)}" for pt in p.points )} ' 'class': 'curve',
if p.method == CurvePath.METHOD.LINE_TO: 'z-index': 2
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'
stroke_col = get_color(item.stroke) if item.height > 0:
fill_col = get_color(item.fill) dy = 1.0/item.height
if fill_col: dx = (item.width/item.height)/(item.x1-item.x0)
path_css['fill'] = fill_col svg_attr.update({
if stroke_col: "viewBox": "0 0 %s %s" % ( item.width/item.height, 1 )
path_css['stroke'] = stroke_col })
else:
dx = 1.0/(item.x1-item.x0)
dy = 1.0
svg_attr.update({
"viewBox": "0 0 1 1"
})
with html.elm('svg', svg_attr, css): if item.height > 1:
html.singleton('path', { svg_attr.update({
"d": path, 'height': f'{item.height}px',
**path_css })
}, { else:
**path_css svg_attr.update({
}) 'height': '1px',
})
if item.width > 1:
svg_attr.update({
'width': f'{item.width}px',
})
else:
svg_attr.update({
'width': '1px',
})
def pX(val: float) -> float:
return ( val-item.x0 )*dx
def pY(val: float) -> float:
return ( item.height- (val-item.y0) )*dy
for p in item.paths:
if p.method == CurvePath.METHOD.MOVE_TO:
path += f'M{" ".join( f"{pX(p.x)} {pY(p.y)}" for p in p.points )} '
elif p.method == CurvePath.METHOD.LINE_TO:
path += f'L{" ".join( f"{pX(p.x)} {pY(p.y)}" for p in p.points )} '
elif p.method == CurvePath.METHOD.CLOSE_PATH:
path += 'Z'
elif p.method == CurvePath.METHOD.CURVE_BOTH_TO:
path += f'C{" ".join( f"{pX(pt.x)} {pY(pt.y)}" for pt in p.points )} '
return path, svg_attr
# def render_textblock(html: HTMLMaker, ltpage: PageInterpreter, item: LTTextBlock):
# (x0, y0, x1, y1) = (INF, INF, -INF, -INF)
# for c_block in item:
# x0 = min(x0, c_block.x0)
# y0 = min(y0, c_block.y0)
# x1 = max(x1, c_block.x1)
# y1 = max(y1, c_block.y1)
# with html.elm('span')
+2 -3
View File
@@ -56,7 +56,6 @@ class HTMLMaker:
self.write(f"<{tag_name} {attrs} />", lineend=lineend, deep_space=deep_space) self.write(f"<{tag_name} {attrs} />", lineend=lineend, deep_space=deep_space)
yield yield
def singleton(self, tag_name: str, attrs: dict = None, css: dict = None): def singleton(self, tag_name: str, attrs: dict = None, css: dict = None, singleton: bool = True):
with self.elm(tag_name, attrs, css, singleton=True): with self.elm(tag_name, attrs, css, singleton=singleton):
pass pass
+117
View File
@@ -0,0 +1,117 @@
from json import dumps as json_dump
from io import TextIOWrapper
from contextlib import contextmanager
@contextmanager
def YAMLMaker(file_path: str, codec: str = 'utf-8'):
with open(file_path, 'wb') as outf:
with YAMLMakerObject(outf, codec=codec) as obj:
yield obj
class YAMLMakerWriter:
class AccessError(Exception): pass
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1):
self.outfile: TextIOWrapper = outfile
self.codec = codec
self.levels_deep = levels_deep
def __enter__(self):
if self.levels_deep > 0:
self.__write_raw('')
self.levels_deep += 1
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.levels_deep -= 1
def __write_raw(self, text):
if self.outfile is not None:
if self.codec:
text = text.encode(self.codec)
self.outfile.write(text)
else:
raise self.AccessError("Attempting to write to file without an open connection")
def _write(self, text: str, append_deep: bool = True, deep_space: str = ' ', prefix:str = ''):
if not append_deep:
deep_space = ""
text = prefix + (deep_space*self.levels_deep) + text
self.__write_raw(text)
class YAMLMakerObject(YAMLMakerWriter):
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1, parent_is_array: bool = False):
YAMLMakerWriter.__init__(self, outfile, codec, levels_deep)
self.keys = set()
self.parent_is_array = parent_is_array
def write(self, key: str, value: str):
if key not in self.keys:
self.keys.add(key)
if len(self.keys) > 1:
self._write(f'{key}: {value}', prefix='\n')
else:
self._write(f'{key}: {value}', prefix='',
append_deep=not self.parent_is_array
)
@contextmanager
def object(self, key: str):
if key not in self.keys:
self.keys.add(key)
if len(self.keys) > 1:
self._write(f'{key}:\n', prefix='\n')
else:
self._write(f'{key}:\n', prefix='', append_deep=False)
with YAMLMakerObject(self.outfile, codec=self.codec, levels_deep=self.levels_deep) as obj:
yield obj
@contextmanager
def array(self, key: str):
if key not in self.keys:
self.keys.add(key)
if len(self.keys) > 1:
self._write(f'{key}:\n', prefix='\n')
else:
self._write(f'{key}:\n', prefix='')
with YAMLMakerArray(self.outfile, codec=self.codec, levels_deep=self.levels_deep) as obj:
yield obj
def place_object(self, key: str, obj: dict):
with self.object(key) as child:
for key, val in obj.items():
child.write(key, val)
def place_array(self, key: str, arr: list):
with self.array(key) as child:
for val in arr:
child.write(val)
class YAMLMakerArray(YAMLMakerWriter):
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1):
YAMLMakerWriter.__init__(self, outfile, codec, levels_deep)
self.childrencount = 0
def write(self, value: str = ""):
self.childrencount += 1
if self.childrencount > 1:
self._write(f'- {value}', prefix='\n')
else:
self._write(f'- {value}', prefix='')
@contextmanager
def object(self):
self.childrencount += 1
if self.childrencount > 1:
self._write(f'- ', prefix='\n')
else:
self._write(f'- ', prefix='')
with YAMLMakerObject(self.outfile, codec=self.codec, levels_deep=self.levels_deep, parent_is_array=True) as obj:
yield obj
def place_object(self, obj: dict):
with self.object() as child:
for key, val in obj.items():
child.write(key, val)
+144
View File
@@ -0,0 +1,144 @@
from typing import List
from .writers.yaml import YAMLMaker, YAMLMakerObject, YAMLMakerArray
from ..interpreter import PDFInterpreter, PageInterpreter, logging
from ..interpreter import LTImage, LTTextBlock, LTCharBlock, LTCurve, LTXObject
from ..interpreter.commands import LTItem
from ..interpreter.commands import LTRect, LTLine
from ..interpreter.commands.state import CurvePath, PDFColor
from ..parser.PSStackParser import PSLiteral
from ..utils import enc
def normalize_color_values(values: list):
ret = []
for v in values:
if isinstance(v, PSLiteral):
ret.append( enc(str(v.name)).decode() )
else:
ret.append( enc(str(v)).decode() )
return ret
def convert_to_yaml(
input_file_path: str,
output_file_path: str,
image_folder_path: str = None,
dont_export_images: bool = False,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
debug_level: int = logging.WARNING,
):
intepreter = PDFInterpreter(input_file_path,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=check_extractable,
pagenos=pagenos,
debug_level=debug_level
)
with YAMLMaker(output_file_path, codec=codec) as yaml:
with yaml.array("pages") as arr:
for page in intepreter:
with arr.object() as page_obj:
render_page(page_obj, page)
def render_page(yaml: YAMLMakerObject, ltpage: PageInterpreter):
yaml.write("id", ltpage.page_num)
yaml.write("width", ltpage.width)
yaml.write("height", ltpage.height)
with yaml.array("children") as chil_arr:
for child in ltpage:
with chil_arr.object() as chil_obj:
render(chil_obj, child)
def render(yaml: YAMLMakerObject, item: LTItem):
if isinstance(item, LTCurve):
place_curve(yaml, item)
elif isinstance(item, LTXObject):
yaml.write("type", 'xobject')
yaml.write("x0", item.x0)
yaml.write("x1", item.x1)
yaml.write("y0", item.y0)
yaml.write("y1", item.y1)
with yaml.array("children") as chil_arr:
for child in item:
with chil_arr.object() as chil_obj:
render(chil_obj, child)
elif isinstance(item, LTImage):
# if yaml.imagewriter is not None:
# name = yaml.imagewriter.export_image(item)
yaml.write("type", 'img')
yaml.write("src", enc(item.name, None))
yaml.write("x0", item.x0)
yaml.write("x1", item.x1)
yaml.write("y0", item.y0)
yaml.write("y1", item.y1)
elif isinstance(item, LTTextBlock):
place_text_block(yaml, item)
def place_text_block(yaml: YAMLMakerObject, text_block: LTTextBlock):
yaml.write("type", 'text-block')
yaml.write("x0", text_block.x0)
yaml.write("x1", text_block.x1)
yaml.write("y0", text_block.y0)
yaml.write("y1", text_block.y1)
with yaml.array("char_blocks") as cb_arr:
for cb in text_block:
with cb_arr.object() as cb_obj:
place_char_block(cb_obj, cb)
def place_char_block(yaml: YAMLMakerObject, char_block: LTCharBlock):
yaml.write("size", char_block.size)
yaml.write("x0", char_block.x0)
yaml.write("x1", char_block.x1)
yaml.write("y0", char_block.y0)
yaml.write("y1", char_block.y1)
if char_block.color.color_space is not None:
yaml.place_object("color", {
"type": enc(char_block.color.color_space.name).decode(),
"value": normalize_color_values(char_block.color.values)
})
for key, value in char_block.font.descriptor.items():
if key != "Type" and "FontFile" not in key:
yaml.write(key, value)
yaml.write("text",
"".join([
char.get_text()
for char in char_block
])
)
def place_curve(yaml: YAMLMakerObject, item: LTCurve):
if isinstance(item, LTRect):
yaml.write("type", 'rect')
elif isinstance(item, LTLine):
yaml.write("type", 'line')
else:
yaml.write("type", 'curve')
with yaml.array('paths') as paths_arr:
for path in item.paths:
paths_arr.place_object({
"type": path.method.name,
"points": [
{"x": point.x, "y": point.y}
for point in path.points
]
})
yaml.write("x0", item.x0)
yaml.write("x1", item.x1)
yaml.write("y0", item.y0)
yaml.write("y1", item.y1)
if item.fill.color_space is not None:
yaml.place_object("fill", {
"type": enc(item.fill.color_space.name).decode(),
"value": normalize_color_values(item.fill.values)
})
if item.stroke.color_space is not None:
yaml.place_object("stroke", {
"type": enc(item.stroke.color_space.name).decode(),
"value": normalize_color_values(item.stroke.values)
})
+2 -4
View File
@@ -20,8 +20,6 @@ log = get_logger('process_command_stream')
class CommandProcessorError(Exception): pass class CommandProcessorError(Exception): pass
def process_command_stream(streams: List[PDFStream], font_cache: dict = None, state: PDFStateStack = None): def process_command_stream(streams: List[PDFStream], font_cache: dict = None, state: PDFStateStack = None):
if state is None:
state = PDFStateStack()
if font_cache is None: if font_cache is None:
font_cache = {} font_cache = {}
parser = PDFContentParser(streams) parser = PDFContentParser(streams)
@@ -41,14 +39,14 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
else: else:
func(state) func(state)
else: else:
log.warning('Unknown operator: %r (i.e. %r)' % (name, method)) log.debug('Unknown operator: %r (i.e. %r)' % (name, method))
else: else:
state.argstack.append(obj) state.argstack.append(obj)
for complete_item in state.complete_layout_items: for complete_item in state.complete_layout_items:
if isinstance(complete_item, LTXObject): if isinstance(complete_item, LTXObject):
xobj_state = prep_state( xobj_state = prep_state(
state=PDFGraphicState(), state=PDFStateStack(),
ctm=complete_item.t_matrix, ctm=complete_item.t_matrix,
resources=complete_item.resources, resources=complete_item.resources,
font_cache=font_cache font_cache=font_cache
+14 -14
View File
@@ -116,7 +116,7 @@ def do_i(stack: PDFStateStack, flatness) -> PDFStateStack:
def do_m(stack: PDFStateStack, x: float, y: float) -> PDFStateStack: def do_m(stack: PDFStateStack, x: float, y: float) -> PDFStateStack:
stack.curvestacks.append(CurvePath( stack.curvestacks.append(CurvePath(
CurvePath.METHOD.MOVE_TO, CurvePath.METHOD.MOVE_TO,
CurvePoint(x, y) CurvePoint(stack.t_matrix, x, y)
)) ))
return stack return stack
@@ -125,7 +125,7 @@ def do_m(stack: PDFStateStack, x: float, y: float) -> PDFStateStack:
def do_l(stack: PDFStateStack, x: float, y: float) -> PDFStateStack: def do_l(stack: PDFStateStack, x: float, y: float) -> PDFStateStack:
stack.curvestacks.append(CurvePath( stack.curvestacks.append(CurvePath(
CurvePath.METHOD.LINE_TO, CurvePath.METHOD.LINE_TO,
CurvePoint(x, y) CurvePoint(stack.t_matrix, x, y)
)) ))
return stack return stack
@@ -137,9 +137,9 @@ def do_c(stack: PDFStateStack,
x3: float, y3: float ) -> PDFStateStack: x3: float, y3: float ) -> PDFStateStack:
stack.curvestacks.append(CurvePath( stack.curvestacks.append(CurvePath(
CurvePath.METHOD.CURVE_BOTH_TO, CurvePath.METHOD.CURVE_BOTH_TO,
CurvePoint(x1, y1), CurvePoint(stack.t_matrix, x1, y1),
CurvePoint(x2, y2), CurvePoint(stack.t_matrix, x2, y2),
CurvePoint(x3, y3), CurvePoint(stack.t_matrix, x3, y3),
)) ))
return stack return stack
@@ -150,8 +150,8 @@ def do_v(stack: PDFStateStack,
x3: float, y3: float) -> PDFStateStack: x3: float, y3: float) -> PDFStateStack:
stack.curvestacks.append(CurvePath( stack.curvestacks.append(CurvePath(
CurvePath.METHOD.CURVE_NEXT_TO, CurvePath.METHOD.CURVE_NEXT_TO,
CurvePoint(x2, y2), CurvePoint(stack.t_matrix, x2, y2),
CurvePoint(x3, y3), CurvePoint(stack.t_matrix, x3, y3),
)) ))
return stack return stack
@@ -162,8 +162,8 @@ def do_y(stack: PDFStateStack,
x3: float, y3: float) -> PDFStateStack: x3: float, y3: float) -> PDFStateStack:
stack.curvestacks.append(CurvePath( stack.curvestacks.append(CurvePath(
CurvePath.METHOD.CURVE_FIRST_TO, CurvePath.METHOD.CURVE_FIRST_TO,
CurvePoint(x1, y1), CurvePoint(stack.t_matrix, x1, y1),
CurvePoint(x3, y3) CurvePoint(stack.t_matrix, x3, y3)
)) ))
return stack return stack
@@ -177,10 +177,10 @@ def do_h(stack: PDFStateStack) -> PDFStateStack:
@PDFCommands.add('re') @PDFCommands.add('re')
def do_re(stack: PDFStateStack, x, y, w, h) -> PDFStateStack: def do_re(stack: PDFStateStack, x, y, w, h) -> PDFStateStack:
stack.curvestacks.extend([ stack.curvestacks.extend([
CurvePath(CurvePath.METHOD.MOVE_TO, CurvePoint(x, y) ), CurvePath(CurvePath.METHOD.MOVE_TO, CurvePoint(stack.t_matrix, x, y) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(x+w, y) ), CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(stack.t_matrix, x+w, y) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(x+w, y+h) ), CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(stack.t_matrix, x+w, y+h) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(x, y+h) ), CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(stack.t_matrix, x, y+h) ),
CurvePath(CurvePath.METHOD.CLOSE_PATH) CurvePath(CurvePath.METHOD.CLOSE_PATH)
]) ])
return stack return stack
@@ -476,7 +476,7 @@ def do__w(stack: PDFStateStack, wordspace, charspace, b) -> PDFStateStack:
def do_EI(stack: PDFStateStack, obj) -> PDFStateStack: def do_EI(stack: PDFStateStack, obj) -> PDFStateStack:
if 'W' in obj and 'H' in obj: if 'W' in obj and 'H' in obj:
stack.complete_layout_items.append(make_image( stack.complete_layout_items.append(make_image(
obj, stack.ctm obj, stack.t_matrix
)) ))
return stack return stack
@@ -1,8 +1,14 @@
from enum import Enum from enum import Enum
from typing import List from typing import List
from pdfmajor.utils import apply_matrix_pt
class CurvePoint: class CurvePoint:
def __init__(self, x: float, y: float): def __init__(self, ctm: tuple, x: float, y: float):
# old = (x,y)
# (x, y) = apply_matrix_pt(ctm, (x, y))
# if old != (x,y):
# print("CurvePoint", ctm, old)
# print(" >", x, y)
self.x = x self.x = x
self.y = y self.y = y
+6
View File
@@ -13,6 +13,12 @@ class Bbox:
self.x1 = x1 self.x1 = x1
self.y0 = y0 self.y0 = y0
self.y1 = y1 self.y1 = y1
if (x0 is not None) and (x1 is not None):
self.x0 = min([x0,x1])
self.x1 = max([x0,x1])
if (y0 is not None) and (y1 is not None):
self.y0 = min([y0,y1])
self.y1 = max([y0,y1])
@property @property
def height(self) -> float: def height(self) -> float:
+1 -1
View File
@@ -10,7 +10,7 @@ import sys
with open('README.md') as readme_file: with open('README.md') as readme_file:
SETUP = { SETUP = {
"name": "pdfmajor", "name": "pdfmajor",
"version": "1.3.2b", "version": "1.3.5",
"packages": find_packages(include=['pdfmajor*']), "packages": find_packages(include=['pdfmajor*']),
"install_requires": [ "install_requires": [
'pycryptodome', 'pycryptodome',
Binary file not shown.
+90
View File
@@ -0,0 +1,90 @@
from os import remove
from tempfile import mktemp
from pdfmajor.converters.writers.yaml import YAMLMaker
# Make temp file
FILE_NAME = mktemp()
with YAMLMaker(FILE_NAME) as yml:
yml.write("name", "bob")
yml.write("age", "20")
with yml.object("wife") as wife:
wife.write("name", "kory")
wife.write("age", "21")
with yml.array("children") as children:
with children.object() as child:
child.write("name", "Mike")
with child.array("toys") as toys:
toys.write("lion")
toys.write("bear")
with yml.object("computer") as computer:
computer.write("type", "awesome")
print(open(FILE_NAME, 'r').read())
assert(open(FILE_NAME, 'r').read() == """name: bob
age: 20
wife:
name: kory
age: 21
children:
- name: Mike
toys:
- lion
- bear
computer:
type: awesome""")
with YAMLMaker(FILE_NAME) as yml:
yml.write("name", "bob")
yml.write("age", "20")
yml.place_object("wife", {
"name": "kory",
"age": 21
})
with yml.array("children") as children:
with children.object() as child:
child.write("name", "Mike")
child.place_array("toys", [
"lion", "bear"
])
yml.place_object("computer", {"type": "awesome"})
print(open(FILE_NAME, 'r').read())
assert(open(FILE_NAME, 'r').read() == """name: bob
age: 20
wife:
name: kory
age: 21
children:
- name: Mike
toys:
- lion
- bear
computer:
type: awesome""")
with YAMLMaker(FILE_NAME) as yml:
with yml.array('pages') as pages:
with pages.object() as page:
page.write("id", 0)
page.write("width", 100)
page.write("height", 200)
with page.array("children") as children:
with children.object() as curve:
with curve.object("stroke") as fill:
fill.write("type", "DeviceRGB")
fill.write("value", ['1','2','3'])
curve.write("x0", 0)
curve.write("x1", 1)
with curve.object("fill") as fill:
fill.write("type", "DeviceRGB")
fill.write("value", ['1','2','3'])
curve.write("y0", 0)
curve.write("y1", 1)
print(open(FILE_NAME, 'r').read())
assert(open(FILE_NAME, 'r').read() == """""")
# Clean up
remove(FILE_NAME)
+4 -5
View File
@@ -52,11 +52,10 @@ def main(args=None):
if len(parsed_args.files) == 1: if len(parsed_args.files) == 1:
if parsed_args.output_file != "-": if parsed_args.output_file != "-":
func_args['output_file'] = open(parsed_args.output_file, "wb") func_args['output_file'] = open(parsed_args.output_file, "wb")
with open(parsed_args.files[0], 'rb') as input_file: convert_file(
convert_file( parsed_args.files[0],
input_file, **func_args
**func_args )
)
else: else:
print("Multiple files not supported yet.") print("Multiple files not supported yet.")
return 1 return 1