zacc806
/
pdfminer.six
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

bugfix (thanks to Brian Berry). 

Remaining TODOs: automatic testing for vertical texts. Various layout analysis tuning.


git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@193 1aa58f4a-7d42-0410-adbc-911cccaed67c
pull/1/head
yusuke.shinyama.dummy 2010-03-22 08:36:39 +00:00
parent 25636d7c08
commit ee34d8d549
2 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
pdfminer/pdfdevice.py
View File

@ -83,16 +83,16 @@ class PDFTextDevice(PDFDevice):
for obj in seq:
if isinstance(obj, int) or isinstance(obj, float):
x -= obj*dxscale
needcharspace = False
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
x += charspace
x += self.render_char(translate_matrix(matrix, (x,y)),
font, fontsize, scaling, cid)
needcharspace = True
if cid == 32 and wordspace:
x += wordspace
needcharspace = True
return (x, y)
def render_string_vertical(self, seq, matrix, (x,y),
@ -101,16 +101,16 @@ class PDFTextDevice(PDFDevice):
for obj in seq:
if isinstance(obj, int) or isinstance(obj, float):
y -= obj*dxscale
needcharspace = False
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
y += charspace
y += self.render_char(translate_matrix(matrix, (x,y)),
font, fontsize, scaling, cid)
needcharspace = True
if cid == 32 and wordspace:
y += wordspace
needcharspace = True
return (x, y)
def render_char(self, matrix, font, fontsize, scaling, cid):

16
tools/pdf2txt.py
View File

@ -11,12 +11,12 @@ from pdfminer.layout import LAParams
def main(argv):
import getopt
def usage():
print ('usage: %s [-d] [-p pagenos] [-P password] [-c codec] '
print ('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output] '
'[-n] [-D direction] [-M char_margin] [-L line_margin] [-W word_margin] '
'[-t text|html|xml|tag] [-O output_dir] [-o output] file ...' % argv[0])
'[-O output_dir] [-t text|html|xml|tag] [-c codec] [-s scale] file ...' % argv[0])
return 100
try:
(opts, args) = getopt.getopt(argv[1:], 'dp:P:c:nD:M:L:W:t:O:o:C:D:m:')
(opts, args) = getopt.getopt(argv[1:], 'dp:m:P:o:nD:M:L:W:O:t:c:s:')
except getopt.GetoptError:
return usage()
if not args: return usage()
@ -37,19 +37,19 @@ def main(argv):
laparams = LAParams()
for (k, v) in opts:
if k == '-d': debug += 1
elif k == '-P': password = v
elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
elif k == '-m': maxpages = int(v)
elif k == '-t': outtype = v
elif k == '-c': codec = v
elif k == '-P': password = v
elif k == '-o': outfile = v
elif k == '-O': outdir = v
elif k == '-s': scale = float(v)
elif k == '-n': laparams = None
elif k == '-D': laparams.direction = v
elif k == '-M': laparams.char_margin = float(v)
elif k == '-L': laparams.line_margin = float(v)
elif k == '-W': laparams.word_margin = float(v)
elif k == '-O': outdir = v
elif k == '-t': outtype = v
elif k == '-c': codec = v
elif k == '-s': scale = float(v)
#
CMapDB.debug = debug
PDFResourceManager.debug = debug