yujunjun/OCRmyPDF
1
0
Fork 0
mirror of https://github.com/ocrmypdf/OCRmyPDF.git synced 2025-12-29 08:01:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

hocrTranform.py: A4 page size corrected

Browse Source
This commit is contained in:
fritz-hh 2013-04-10 16:22:15 +03:00
parent 8fdbfc3c95
commit c51babfd27
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
hocrTransform.py
View File

@ -97,8 +97,6 @@ class hocrTransform():
The image need not be identical to the image used to create the hOCR file.
It can have a lower resolution, different color mode, etc.
"""
im = Image.open(imageFileName)
# get dimension of the OCRed image
for div in self.hocr.findall(".//%sdiv[@class='ocr_page']"%(self.xmlns)):
coords = self.element_coordinates(div)
@ -111,13 +109,14 @@ class hocrTransform():
# assuming page size is A4
print "page width and height not available in %s. Assuming A4."%(imageFileName)
width = 21*2.54*inch
height = 29.6*2.54*inch
height = 29.7*2.54*inch
# create the PDF file
pdf = Canvas(outFileName, pagesize=(width, height), pageCompression=1) # page size in points (1/72 in.)
# put the image on the page, scaled to fill the page
#pdf.drawInlineImage(im, 0, 0, width=width, height=height)
im = Image.open(imageFileName)
pdf.drawInlineImage(im, 0, 0, width=width, height=height)
# check if element with class 'ocrx_word' are available
# otherwise use 'ocr_line' as fallback