Merge branch 'feature/leptdeskew' into feature/logging
Need leptonica for testing now, I think # Conflicts: # ocrmypdf/tesseract.py # requirements.txt # setup.py
This commit is contained in:
James R. Barlow
+21
-83
@@ -10,11 +10,14 @@
|
||||
|
||||
from __future__ import print_function, absolute_import, division
|
||||
import argparse
|
||||
import ctypes as C
|
||||
import sys
|
||||
import os
|
||||
import logging
|
||||
from tempfile import TemporaryFile
|
||||
from ctypes.util import find_library
|
||||
from .lib._leptonica import ffi
|
||||
|
||||
lept = ffi.dlopen(find_library('lept'))
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -25,67 +28,6 @@ def stderr(*objs):
|
||||
print("leptonica.py:", *objs, file=sys.stderr)
|
||||
|
||||
|
||||
from ctypes.util import find_library
|
||||
lept_lib = find_library('lept')
|
||||
if not lept_lib:
|
||||
stderr("Could not find the Leptonica library")
|
||||
sys.exit(3)
|
||||
try:
|
||||
lept = C.cdll.LoadLibrary(lept_lib)
|
||||
except Exception:
|
||||
stderr("Could not load the Leptonica library from %s", lept_lib)
|
||||
sys.exit(3)
|
||||
|
||||
|
||||
class _PIXCOLORMAP(C.Structure):
|
||||
"""struct PixColormap from Leptonica src/pix.h
|
||||
"""
|
||||
|
||||
_fields_ = [
|
||||
("array", C.c_void_p),
|
||||
("depth", C.c_int32),
|
||||
("nalloc", C.c_int32),
|
||||
("n", C.c_int32)
|
||||
]
|
||||
|
||||
|
||||
class _PIX(C.Structure):
|
||||
"""struct Pix from Leptonica src/pix.h
|
||||
"""
|
||||
|
||||
_fields_ = [
|
||||
("w", C.c_uint32),
|
||||
("h", C.c_uint32),
|
||||
("d", C.c_uint32),
|
||||
("wpl", C.c_uint32),
|
||||
("refcount", C.c_uint32),
|
||||
("xres", C.c_int32),
|
||||
("yres", C.c_int32),
|
||||
("informat", C.c_int32),
|
||||
("text", C.POINTER(C.c_char)),
|
||||
("colormap", C.POINTER(_PIXCOLORMAP)),
|
||||
("data", C.POINTER(C.c_uint32))
|
||||
]
|
||||
|
||||
|
||||
PIX = C.POINTER(_PIX)
|
||||
|
||||
lept.pixRead.argtypes = [C.c_char_p]
|
||||
lept.pixRead.restype = PIX
|
||||
lept.pixScale.argtypes = [PIX, C.c_float, C.c_float]
|
||||
lept.pixScale.restype = PIX
|
||||
lept.pixDeskew.argtypes = [PIX, C.c_int32]
|
||||
lept.pixDeskew.restype = PIX
|
||||
lept.pixFindSkew.argtypes = [PIX, C.POINTER(C.c_float), C.POINTER(C.c_float)]
|
||||
lept.pixFindSkew.restype = C.c_int32
|
||||
lept.pixWriteImpliedFormat.argtypes = [C.c_char_p, PIX, C.c_int32, C.c_int32]
|
||||
lept.pixWriteImpliedFormat.restype = C.c_int32
|
||||
lept.pixDestroy.argtypes = [C.POINTER(PIX)]
|
||||
lept.pixDestroy.restype = None
|
||||
lept.getLeptonicaVersion.argtypes = []
|
||||
lept.getLeptonicaVersion.restype = C.c_char_p
|
||||
|
||||
|
||||
class LeptonicaErrorTrap(object):
|
||||
"""Context manager to trap errors reported by Leptonica.
|
||||
|
||||
@@ -140,6 +82,12 @@ class LeptonicaIOError(LeptonicaError):
|
||||
pass
|
||||
|
||||
|
||||
def _pix_destroy(pix):
|
||||
ptr_to_pix = ffi.new('PIX **', pix)
|
||||
lept.pixDestroy(ptr_to_pix)
|
||||
print('pix destroy ' + repr(pix))
|
||||
|
||||
|
||||
def pixRead(filename):
|
||||
"""Load an image file into a PIX object.
|
||||
|
||||
@@ -148,7 +96,8 @@ def pixRead(filename):
|
||||
|
||||
"""
|
||||
with LeptonicaErrorTrap():
|
||||
return lept.pixRead(filename.encode(sys.getfilesystemencoding()))
|
||||
pix = lept.pixRead(filename.encode(sys.getfilesystemencoding()))
|
||||
return ffi.gc(pix, _pix_destroy)
|
||||
|
||||
|
||||
def pixScale(pix, scalex, scaley):
|
||||
@@ -168,7 +117,8 @@ def pixDeskew(pix, reduction_factor=0):
|
||||
|
||||
"""
|
||||
with LeptonicaErrorTrap():
|
||||
return lept.pixDeskew(pix, reduction_factor)
|
||||
deskewed = lept.pixDeskew(pix, reduction_factor)
|
||||
return ffi.gc(deskewed, _pix_destroy)
|
||||
|
||||
|
||||
def pixFindSkew(pix):
|
||||
@@ -178,11 +128,11 @@ def pixFindSkew(pix):
|
||||
|
||||
"""
|
||||
with LeptonicaErrorTrap():
|
||||
angle = C.c_float(0.0)
|
||||
confidence = C.c_float(0.0)
|
||||
result = lept.pixFindSkew(pix, C.byref(angle), C.byref(confidence))
|
||||
angle = ffi.new('float *', 0.0)
|
||||
confidence = ffi.new('float *', 0.0)
|
||||
result = lept.pixFindSkew(pix, angle, confidence)
|
||||
if result == 0:
|
||||
return (angle.value, confidence.value)
|
||||
return (angle[0], confidence[0])
|
||||
else:
|
||||
return (None, None)
|
||||
|
||||
@@ -212,17 +162,6 @@ def pixWriteImpliedFormat(filename, pix, jpeg_quality=0, jpeg_progressive=0):
|
||||
move(filename, filename[:-4]) # Remove .pnm suffix
|
||||
|
||||
|
||||
def pixDestroy(pix):
|
||||
"""Destroy the pix object.
|
||||
|
||||
Function signature is pixDestroy(struct Pix **), hence C.byref() to pass
|
||||
the address of the pointer.
|
||||
|
||||
"""
|
||||
with LeptonicaErrorTrap():
|
||||
lept.pixDestroy(C.byref(pix))
|
||||
|
||||
|
||||
def getLeptonicaVersion():
|
||||
"""Get Leptonica version string.
|
||||
|
||||
@@ -231,12 +170,13 @@ def getLeptonicaVersion():
|
||||
a pointless effort to reclaim 100 bytes of memory.
|
||||
|
||||
"""
|
||||
return lept.getLeptonicaVersion().decode()
|
||||
return ffi.string(lept.getLeptonicaVersion()).decode()
|
||||
|
||||
|
||||
def deskew(infile, outfile, dpi):
|
||||
try:
|
||||
pix_source = pixRead(infile)
|
||||
print(repr(pix_source))
|
||||
except LeptonicaIOError:
|
||||
raise LeptonicaIOError("Failed to open file: %s" % infile)
|
||||
|
||||
@@ -245,13 +185,12 @@ def deskew(infile, outfile, dpi):
|
||||
else:
|
||||
reduction_factor = 0 # Use default
|
||||
pix_deskewed = pixDeskew(pix_source, reduction_factor)
|
||||
print(repr(pix_deskewed))
|
||||
|
||||
try:
|
||||
pixWriteImpliedFormat(outfile, pix_deskewed)
|
||||
except LeptonicaIOError:
|
||||
raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
|
||||
pixDestroy(pix_source)
|
||||
pixDestroy(pix_deskewed)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
@@ -325,7 +264,6 @@ def test_skew_angle():
|
||||
rotated_im.save(tmpfile)
|
||||
pix = pixRead(tmpfile.name)
|
||||
angle, confidence = pixFindSkew(pix)
|
||||
pixDestroy(pix)
|
||||
print('{0} {1} {2}'.format(rotate_angle, angle, confidence), file=sys.stderr)
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
from cffi import FFI
|
||||
|
||||
ffi = FFI()
|
||||
ffi.set_source("ocrmypdf.lib._leptonica", None)
|
||||
ffi.cdef("""
|
||||
typedef signed char l_int8;
|
||||
typedef unsigned char l_uint8;
|
||||
typedef short l_int16;
|
||||
typedef unsigned short l_uint16;
|
||||
typedef int l_int32;
|
||||
typedef unsigned int l_uint32;
|
||||
typedef float l_float32;
|
||||
typedef double l_float64;
|
||||
typedef long long l_int64;
|
||||
typedef unsigned long long l_uint64;
|
||||
|
||||
struct Pix
|
||||
{
|
||||
l_uint32 w; /* width in pixels */
|
||||
l_uint32 h; /* height in pixels */
|
||||
l_uint32 d; /* depth in bits (bpp) */
|
||||
l_uint32 spp; /* number of samples per pixel */
|
||||
l_uint32 wpl; /* 32-bit words/line */
|
||||
l_uint32 refcount; /* reference count (1 if no clones) */
|
||||
l_int32 xres; /* image res (ppi) in x direction */
|
||||
/* (use 0 if unknown) */
|
||||
l_int32 yres; /* image res (ppi) in y direction */
|
||||
/* (use 0 if unknown) */
|
||||
l_int32 informat; /* input file format, IFF_* */
|
||||
l_int32 special; /* special instructions for I/O, etc */
|
||||
char *text; /* text string associated with pix */
|
||||
struct PixColormap *colormap; /* colormap (may be null) */
|
||||
l_uint32 *data; /* the image data */
|
||||
};
|
||||
typedef struct Pix PIX;
|
||||
|
||||
struct PixColormap
|
||||
{
|
||||
void *array; /* colormap table (array of RGBA_QUAD) */
|
||||
l_int32 depth; /* of pix (1, 2, 4 or 8 bpp) */
|
||||
l_int32 nalloc; /* number of color entries allocated */
|
||||
l_int32 n; /* number of color entries used */
|
||||
};
|
||||
typedef struct PixColormap PIXCMAP;
|
||||
""")
|
||||
|
||||
ffi.cdef("""
|
||||
PIX * pixRead ( const char *filename );
|
||||
PIX * pixScale ( PIX *pixs, l_float32 scalex, l_float32 scaley );
|
||||
l_int32 pixFindSkew ( PIX *pixs, l_float32 *pangle, l_float32 *pconf );
|
||||
l_int32 pixWriteImpliedFormat ( const char *filename, PIX *pix, l_int32 quality, l_int32 progressive );
|
||||
void pixDestroy ( PIX **ppix );
|
||||
PIX * pixDeskew ( PIX *pixs, l_int32 redsearch );
|
||||
char * getLeptonicaVersion ( );
|
||||
""")
|
||||
|
||||
if __name__ == '__main__':
|
||||
ffi.compile()
|
||||
+8
-1
@@ -187,6 +187,9 @@ advanced.add_argument(
|
||||
'--tesseract-timeout', default=180.0, type=float, metavar='SECONDS',
|
||||
help='give up on OCR after the timeout, but copy the preprocessed page '
|
||||
'into the final output')
|
||||
advanced.add_argument(
|
||||
'--deskewer', choices=['leptonica', 'unpaper'], default='leptonica',
|
||||
help='choose deskew provider')
|
||||
|
||||
debugging = parser.add_argument_group(
|
||||
"Debugging",
|
||||
@@ -585,7 +588,11 @@ def preprocess_deskew(
|
||||
pageinfo = get_pageinfo(input_file, pdfinfo, pdfinfo_lock)
|
||||
dpi = int(pageinfo['xres'])
|
||||
|
||||
unpaper.deskew(input_file, output_file, dpi, log)
|
||||
if options.deskewer == 'unpaper':
|
||||
unpaper.deskew(input_file, output_file, dpi, log)
|
||||
else:
|
||||
from . import leptonica
|
||||
leptonica.deskew(input_file, output_file, dpi)
|
||||
|
||||
|
||||
@transform(
|
||||
|
||||
@@ -3,3 +3,4 @@ Pillow==3.1.1
|
||||
reportlab==3.2.0
|
||||
PyPDF2==1.25.1
|
||||
img2pdf==0.2
|
||||
cffi>=1.5.0
|
||||
|
||||
@@ -208,15 +208,20 @@ setup(
|
||||
"Topic :: Text Processing :: Linguistic",
|
||||
],
|
||||
setup_requires=[
|
||||
'setuptools_scm'
|
||||
'setuptools_scm',
|
||||
'cffi>=1.0.0'
|
||||
],
|
||||
use_scm_version={'version_scheme': 'post-release'},
|
||||
cffi_modules=[
|
||||
'ocrmypdf/lib/compile_leptonica.py:ffi'
|
||||
],
|
||||
install_requires=[
|
||||
'ruffus>=2.6.3',
|
||||
'Pillow>=2.4.0',
|
||||
'reportlab>=3.1.44',
|
||||
'PyPDF2>=1.25.1',
|
||||
'img2pdf>=0.2.0'
|
||||
'img2pdf>=0.2.0',
|
||||
'cffi>=1.5.0'
|
||||
],
|
||||
tests_require=tests_require,
|
||||
entry_points={
|
||||
|
||||
Reference in New Issue
Block a user