1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
|
From b1d17b605088e118a8799fd027a892310e00d29e Mon Sep 17 00:00:00 2001
From: Hongzhuo Liang <lianghongzhuo@126.com>
Date: Fri, 27 Jan 2023 17:57:04 +0100
Subject: [PATCH] support pikepdf instead of pypdf2
---
krop/mainwindow.py | 1 -
krop/pdfcropper.py | 79 ++++++++++++++--------------------------------
2 files changed, 24 insertions(+), 56 deletions(-)
diff --git a/krop/mainwindow.py b/krop/mainwindow.py
index e8adadf..fd1ae32 100644
--- a/krop/mainwindow.py
+++ b/krop/mainwindow.py
@@ -413,7 +413,6 @@ def slotKrop(self):
pdf = PdfFile()
pdf.loadFromFile(inputFileName)
cropper = PdfCropper()
- cropper.copyDocumentRoot(pdf)
for nr in pages:
c = self.viewer.cropValues(nr)
cropper.addPageCropped(pdf, nr, c, alwaysinclude, rotation)
diff --git a/krop/pdfcropper.py b/krop/pdfcropper.py
index db30646..42500de 100644
--- a/krop/pdfcropper.py
+++ b/krop/pdfcropper.py
@@ -15,23 +15,8 @@
import copy
import sys
+from pikepdf import Pdf
-# Unless specified otherwise, use PyPDF2 instead of pyPdf if available.
-usepypdf2 = '--no-PyPDF2' not in sys.argv
-if usepypdf2:
- try:
- from PyPDF2 import PdfFileReader, PdfFileWriter
- except ImportError:
- usepypdf2 = False
-if not usepypdf2:
- try:
- from pyPdf import PdfFileReader, PdfFileWriter
- except ImportError:
- _msg = "Please install PyPDF2 (or its predecessor pyPdf) first."\
- "\n\tOn recent versions of Ubuntu, the following should do the trick:"\
- "\n\tsudo apt-get install python-pypdf2"\
- "\n\t(or, if using python3) sudo apt-get install python3-pypdf2"
- raise RuntimeError(_msg)
class PdfEncryptedError(Exception):
pass
@@ -55,8 +40,6 @@ def writeToFile(self, filename):
stream.close()
def addPageCropped(self, pdffile, pagenumber, croplist, rotate=0):
pass
- def copyDocumentRoot(self, pdffile):
- pass
class PyPdfFile(AbstractPdfFile):
@@ -64,23 +47,16 @@ class PyPdfFile(AbstractPdfFile):
def __init__(self):
self.reader = None
def loadFromStream(self, stream):
- if usepypdf2:
- self.reader = PdfFileReader(stream, strict=False)
- else:
- self.reader = PdfFileReader(stream)
- if self.reader.isEncrypted:
- try:
- if not self.reader.decrypt(''):
- raise PdfEncryptedError
- except:
- raise PdfEncryptedError
- def getPage(self, nr):
- page = self.reader.getPage(nr-1)
+ self.reader = Pdf.open(stream)
+ if self.reader.is_encrypted:
+ raise PdfEncryptedError
+
class PyPdfCropper(AbstractPdfCropper):
"""Implementation of PdfCropper using pyPdf"""
def __init__(self):
- self.output = PdfFileWriter()
+ self.pdf = Pdf.new()
+
def writeToStream(self, stream):
# For certain large pdf files, PdfFileWriter.write() causes the error:
# maximum recursion depth exceeded while calling a Python object
@@ -88,37 +64,31 @@ def writeToStream(self, stream):
# We therefore temporarily increase the recursion limit.
old_reclimit = sys.getrecursionlimit()
sys.setrecursionlimit(10000)
- self.output.write(stream)
+ self.pdf.save(stream)
sys.setrecursionlimit(old_reclimit)
+
def addPageCropped(self, pdffile, pagenumber, croplist, alwaysinclude, rotate=0):
- page = pdffile.reader.getPage(pagenumber)
+ page = pdffile.reader.pages[pagenumber]
if not croplist and alwaysinclude:
- self.output.addPage(page)
+ self.pdf.pages.append(page)
for c in croplist:
- newpage = copy.copy(page)
- self.cropPage(newpage, c, rotate)
- self.output.addPage(newpage)
- def cropPage(self, page, crop, rotate):
+ new_box = self.getCropPageParm(page, c)
+ # Update the various PDF boxes
+ new_page = copy.copy(page)
+ new_page.mediabox = new_box
+ new_page.cropbox = new_box
+ new_page.trimbox = new_box
+ if rotate != 0:
+ new_page.rotate(rotate, True)
+ self.pdf.pages.append(new_page)
+
+ def getCropPageParm(self, page, crop):
# Note that the coordinate system is up-side down compared with Qt.
- x0, y0 = page.cropBox.lowerLeft
- x1, y1 = page.cropBox.upperRight
+ x0, y0, x1, y1 = page.cropbox
x0, y0, x1, y1 = float(x0), float(y0), float(x1), float(y1)
x0, x1 = x0+crop[0]*(x1-x0), x1-crop[2]*(x1-x0)
y0, y1 = y0+crop[3]*(y1-y0), y1-crop[1]*(y1-y0)
- # Update the various PDF boxes
- for box in (page.artBox, page.bleedBox, page.cropBox, page.mediaBox, page.trimBox):
- box.lowerLeft = (x0, y0)
- box.upperRight = (x1, y1)
- if rotate != 0:
- page.rotateClockwise(rotate)
-
- def copyDocumentRoot(self, pdffile):
- # Sounds promising in PyPDF2 (see PdfFileWriter.cloneDocumentFromReader),
- # but doesn't seem to produce a readable PDF:
- # self.output.cloneReaderDocumentRoot(pdffile.reader)
- # Instead, this copies at least the named destinations for links:
- for dest in pdffile.reader.namedDestinations.values():
- self.output.addNamedDestinationObject(dest)
+ return [x0, y0, x1, y1]
def optimizePdfGhostscript(oldfilename, newfilename):
@@ -128,4 +98,3 @@ def optimizePdfGhostscript(oldfilename, newfilename):
PdfFile = PyPdfFile
PdfCropper = PyPdfCropper
-
|
