pypdf 1.4__tar.gz

pyPdf-1.4/CHANGELOG

@@ -0,0 +1,64 @@
+Version 1.4, 2006-01-27
+-----------------------
+
+- Add capability to merge pages from multiple PDF files into a single page
+  using the PageObject.mergePage function.  See example code (README or web
+  site) for more information.
+
+- Add ability to modify a page's MediaBox, CropBox, BleedBox, TrimBox, and
+  ArtBox properties through PageObject.  See example code (README or web site)
+  for more information.
+
+- Refactor pdf.py into multiple files: generic.py (contains objects like
+  NameObject, DictionaryObject), filters.py (contains filter code),
+  utils.py (various).  This does not affect importing PdfFileReader
+  or PdfFileWriter.
+
+- Add new decoding functions for standard PDF filters ASCIIHexDecode and
+  ASCII85Decode.
+
+- Change url and download_url to refer to new pybrary.net web site.
+
+
+Version 1.3, 2006-01-23
+-----------------------
+
+- Fix new bug introduced in 1.2 where PDF files with \r line endings did not
+  work properly anymore.  A new test suite developed with various PDF files
+  should prevent regression bugs from now on.
+
+- Fix a bug where inheriting attributes from page nodes did not work.
+
+
+Version 1.2, 2006-01-23
+-----------------------
+
+- Improved support for files with CRLF-based line endings, fixing a common
+  reported problem stating "assertion error: assert line == "%%EOF"".
+
+- Software author/maintainer is now officially a proud married person, which
+  is sure to result in better software... somehow.
+
+
+Version 1.1, 2006-01-18
+-----------------------
+
+- Add capability to rotate pages.
+
+- Improved PDF reading support to properly manage inherited attributes from
+  /Type=/Pages nodes.  This means that page groups that are rotated or have
+  different media boxes or whatever will now work properly.
+
+- Added PDF 1.5 support.  Namely cross-reference streams and object streams.
+  This release can mangle Adobe's PDFReference16.pdf successfully.
+
+
+Version 1.0, 2006-01-17
+-----------------------
+
+- First distutils-capable true public release.  Supports a wide variety of PDF
+  files that I found sitting around on my system.
+
+- Does not support some PDF 1.5 features, such as object streams,
+  cross-reference streams.
+

pyPdf-1.4/PKG-INFO

@@ -0,0 +1,29 @@
+Metadata-Version: 1.0
+Name: pyPdf
+Version: 1.4
+Summary: PDF toolkit
+Home-page: http://pybrary.net/pyPdf/
+Author: Mathieu Fenniak
+Author-email: mfenniak@pobox.com
+License: UNKNOWN
+Download-URL: http://pybrary.net/pyPdf/pyPdf-1.4.tar.gz
+Description: 
+        A Pure-Python library built as a PDF toolkit.  It is capable of:
+        
+        - splitting documents page by page,
+        - merging documents page by page,
+        - cropping pages,
+        - merging multiple pages into a single page.
+        
+        By being Pure-Python, it should run on any Python platform without any
+        dependencies on external libraries.  It can also work entirely on StringIO
+        objects rather than file streams, allowing for PDF manipulation in memory.
+        It is therefore a useful tool for websites that manage or manipulate PDFs.
+        
+Platform: UNKNOWN
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Programming Language :: Python
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Software Development :: Libraries :: Python Modules

pyPdf-1.4/README

@@ -0,0 +1,38 @@
+Example:
+
+    from pyPdf import PdfFileWriter, PdfFileReader
+
+    output = PdfFileWriter()
+    input1 = PdfFileReader(file("document1.pdf", "rb"))
+
+    # add page 1 from input1 to output document, unchanged
+    output.addPage(input1.getPage(0))
+
+    # add page 2 from input1, but rotated clockwise 90 degrees
+    output.addPage(input1.getPage(1).rotateClockwise(90))
+
+    # add page 3 from input1, rotated the other way:
+    output.addPage(input1.getPage(2).rotateCounterClockwise(90))
+    # alt: output.addPage(input1.getPage(2).rotateClockwise(270))
+
+    # add page 4 from input1, but first add a watermark from another pdf:
+    page4 = input1.getPage(3)
+    watermark = PdfFileReader(file("watermark.pdf", "rb"))
+    page4.mergePage(watermark.getPage(0))
+
+    # add page 5 from input1, but crop it to half size:
+    page5 = input1.getPage(4)
+    page5.mediaBox.upperRight = (
+        page5.mediaBox.getUpperRight_x() / 2,
+        page5.mediaBox.getUpperRight_y() / 2
+    )
+    output.addPage(page5)
+
+    # print how many pages input1 has:
+    print "document1.pdf has %s pages." % input1.getNumPages())
+
+    # finally, write "output" to document-output.pdf
+    outputStream = file("document-output.pdf", "wb")
+    output.write(outputStream)
+
+

pyPdf-1.4/pyPdf/__init__.py

@@ -0,0 +1,2 @@
+from pdf import PdfFileReader, PdfFileWriter
+__all__ = ["pdf"]

pyPdf-1.4/pyPdf/filters.py

@@ -0,0 +1,178 @@
+# vim: sw=4:expandtab:foldmethod=marker
+#
+# Copyright (c) 2006, Mathieu Fenniak
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are
+# met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+# this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+# this list of conditions and the following disclaimer in the documentation
+# and/or other materials provided with the distribution.
+# * The name of the author may not be used to endorse or promote products
+# derived from this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+
+"""
+Implementation of stream filters for PDF.
+"""
+__author__ = "Mathieu Fenniak"
+__author_email__ = "mfenniak@pobox.com"
+
+import zlib
+from generic import NameObject
+
+class FlateDecode(object):
+    def decode(data, decodeParms):
+        data = zlib.decompress(data)
+        predictor = 1
+        if decodeParms:
+            predictor = decodeParms.get("/Predictor", 1)
+        # predictor 1 == no predictor
+        if predictor != 1:
+            columns = decodeParms["/Columns"]
+            if predictor >= 10:
+                newdata = ""
+                # PNG prediction can vary from row to row
+                rowlength = columns + 1
+                assert len(data) % rowlength == 0
+                prev_rowdata = "\x00"*rowlength
+                for row in range(len(data) / rowlength):
+                    rowdata = list(data[(row*rowlength):((row+1)*rowlength)])
+                    filterByte = ord(rowdata[0])
+                    if filterByte == 0:
+                        pass
+                    elif filterByte == 1:
+                        for i in range(2, rowlength):
+                            rowdata[i] = chr((ord(rowdata[i]) + ord(rowdata[i-1])) % 256)
+                    elif filterByte == 2:
+                        for i in range(1, rowlength):
+                            rowdata[i] = chr((ord(rowdata[i]) + ord(prev_rowdata[i])) % 256)
+                    else:
+                        # unsupported PNG filter
+                        assert False
+                    prev_rowdata = rowdata
+                    newdata += ''.join(rowdata[1:])
+                data = newdata
+            else:
+                # unsupported predictor
+                assert False
+        return data
+    decode = staticmethod(decode)
+
+class ASCIIHexDecode(object):
+    def decode(data, decodeParms=None):
+        retval = ""
+        char = ""
+        x = 0
+        while True:
+            c = data[x]
+            if c == ">":
+                break
+            elif c.isspace():
+                x += 1
+                continue
+            char += c
+            if len(char) == 2:
+                retval += chr(int(char, base=16))
+                char = ""
+            x += 1
+        assert char == ""
+        return retval
+    decode = staticmethod(decode)
+
+class ASCII85Decode(object):
+    def decode(data, decodeParms=None):
+        retval = ""
+        group = []
+        x = 0
+        hitEod = False
+        while not hitEod:
+            c = data[x]
+            if len(retval) == 0 and c == "<" and data[x+1] == "~":
+                x += 2
+                continue
+            elif c.isspace():
+                x += 1
+                continue
+            elif c == 'z':
+                assert len(group) == 0
+                retval += '\x00\x00\x00\x00'
+                continue
+            elif c == "~" and data[x+1] == ">":
+                if len(group) != 0:
+                    # cannot have a final group of just 1 char
+                    assert len(group) > 1
+                    cnt = len(group) - 1
+                    group += [ 85, 85, 85 ]
+                    hitEod = cnt
+                else:
+                    break
+            else:
+                c = ord(c) - 33
+                assert c >= 0 and c < 85
+                group += [ c ]
+            if len(group) >= 5:
+                b = group[0] * (85**4) + \
+                    group[1] * (85**3) + \
+                    group[2] * (85**2) + \
+                    group[3] * 85 + \
+                    group[4]
+                assert b < (2**32 - 1)
+                c4 = chr((b >> 0) % 256)
+                c3 = chr((b >> 8) % 256)
+                c2 = chr((b >> 16) % 256)
+                c1 = chr(b >> 24)
+                retval += (c1 + c2 + c3 + c4)
+                if hitEod:
+                    retval = retval[:-4+hitEod]
+                group = []
+            x += 1
+        return retval
+    decode = staticmethod(decode)
+
+def decodeStreamData(stream):
+    filters = stream.get("/Filter", ())
+    if len(filters) and not isinstance(filters[0], NameObject):
+        # we have a single filter instance
+        filters = (filters,)
+    data = stream['__streamdata__']
+    for filterType in filters:
+        if filterType == "/FlateDecode":
+            data = FlateDecode.decode(data, stream.get("/DecodeParms"))
+        elif filterType == "/ASCIIHexDecode":
+            data = ASCIIHexDecode.decode(data)
+        elif filterType == "/ASCII85Decode":
+            data = ASCII85Decode.decode(data)
+        else:
+            # unsupported filter
+            assert False
+    return data
+
+if __name__ == "__main__":
+    assert "abc" == ASCIIHexDecode.decode('61\n626\n3>')
+
+    ascii85Test = """
+     <~9jqo^BlbD-BleB1DJ+*+F(f,q/0JhKF<GL>Cj@.4Gp$d7F!,L7@<6@)/0JDEF<G%<+EV:2F!,
+     O<DJ+*.@<*K0@<6L(Df-\\0Ec5e;DffZ(EZee.Bl.9pF"AGXBPCsi+DGm>@3BB/F*&OCAfu2/AKY
+     i(DIb:@FD,*)+C]U=@3BN#EcYf8ATD3s@q?d$AftVqCh[NqF<G:8+EV:.+Cf>-FD5W8ARlolDIa
+     l(DId<j@<?3r@:F%a+D58'ATD4$Bl@l3De:,-DJs`8ARoFb/0JMK@qB4^F!,R<AKZ&-DfTqBG%G
+     >uD.RTpAKYo'+CT/5+Cei#DII?(E,9)oF*2M7/c~>
+    """
+    ascii85_originalText="Man is distinguished, not only by his reason, but by this singular passion from other animals, which is a lust of the mind, that by a perseverance of delight in the continued and indefatigable generation of knowledge, exceeds the short vehemence of any carnal pleasure."
+    assert ASCII85Decode.decode(ascii85Test) == ascii85_originalText