menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

The Great Logging Refactor

Browse Source 
Remove all instances of logger object being passed as parameters.
This was a holdover from ruffus, and complicated a lot of simple things.
This commit is contained in:
James R. Barlow
2020-04-14 23:59:33 -07:00
parent 4ff4ed24a8
commit d146d2b65c
19 changed files with 107 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ocrmypdf/exec/__init__.py
-3
View File
@@ -268,9 +268,6 @@ def check_external_program(
recommended=False,
**kwargs, # To consume log parameter
):
if kwargs:
if not 'log' in kwargs:
log.warning('check_external_program(log=...) is deprecated')
try:
found_version = version_checker()
except (CalledProcessError, FileNotFoundError, MissingDependencyError):
src/ocrmypdf/exec/ghostscript.py
+1 -9
View File
@@ -34,7 +34,7 @@ from PIL import Image
from ..exceptions import MissingDependencyError, SubprocessOutputError
from . import get_version, run
gslog = logging.getLogger()
log = logging.getLogger(__name__)
GS = 'gs'
if os.name == 'nt':
@@ -138,7 +138,6 @@ def rasterize_pdf(
xres,
yres,
raster_device,
log,
pageno=1,
page_dpi=None,
rotation=None,
@@ -155,7 +154,6 @@ def rasterize_pdf(
:param xres: resolution at which to rasterize page
:param yres:
:param raster_device:
:param log:
:param pageno: page number to rasterize (beginning at page 1)
:param page_dpi: resolution tuple (x, y) overriding output image DPI
:param rotation: 0, 90, 180, 270: clockwise angle to rotate page
@@ -165,8 +163,6 @@ def rasterize_pdf(
res = round(xres, 6), round(yres, 6)
if not page_dpi:
page_dpi = res
if not log:
log = gslog
args_gs = (
[
@@ -191,7 +187,6 @@ def rasterize_pdf(
]
)
log.debug(args_gs)
try:
p = run(args_gs, stdout=PIPE, stderr=PIPE, check=True)
except CalledProcessError as e:
@@ -224,7 +219,6 @@ def generate_pdfa(
pdf_pages,
output_file,
compression,
log,
threads=None, # deprecated parameter
pdf_version='1.5',
pdfa_part='2',
@@ -246,8 +240,6 @@ def generate_pdfa(
images entirely. (The feature was added in 9.23 but broken, and the 9.24
release of Ghostscript had regressions, so we don't support it until 9.25.)
"""
if not log:
log = gslog
if threads is not None:
warnings.warn(
"use of deprecated parameter 'threads'", category=DeprecationWarning
src/ocrmypdf/exec/qpdf.py
+5 -3
View File
@@ -17,22 +17,24 @@
"""Interface to qpdf executable"""
import logging
from io import StringIO
import pikepdf
log = logging.getLogger(__name__)
def version():
return pikepdf.__libqpdf_version__
def check(input_file, log=None):
def check(input_file):
pdf = None
try:
pdf = pikepdf.open(input_file)
except pikepdf.PdfError as e:
if log:
log.error(e)
log.error(e)
return False
else:
messages = pdf.check()
src/ocrmypdf/exec/tesseract.py
+21 -21
View File
@@ -33,6 +33,8 @@ from ..exceptions import (
from ..helpers import page_number, safe_symlink
from . import get_version, run
log = logging.getLogger(__name__)
OrientationConfidence = namedtuple('OrientationConfidence', ('angle', 'confidence'))
HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
@@ -144,7 +146,7 @@ def tess_base_args(langs, engine_mode):
return args
def get_orientation(input_file, engine_mode, timeout: float, log, tesseract_env=None):
def get_orientation(input_file, engine_mode, timeout: float, tesseract_env=None):
args_tesseract = tess_base_args(['osd'], engine_mode) + [
'--psm',
'0',
@@ -165,7 +167,7 @@ def get_orientation(input_file, engine_mode, timeout: float, log, tesseract_env=
except TimeoutExpired:
return OrientationConfidence(angle=0, confidence=0.0)
except CalledProcessError as e:
tesseract_log_output(log, e.output, input_file)
tesseract_log_output(e.output, input_file)
if (
b'Too few characters. Skipping this page' in e.output
or b'Image too large' in e.output
@@ -187,9 +189,9 @@ def get_orientation(input_file, engine_mode, timeout: float, log, tesseract_env=
return oc
def tesseract_log_output(mainlog, stdout, input_file):
log = TesseractLoggerAdapter(
mainlog, extra=mainlog.extra if hasattr(mainlog, 'extra') else None
def tesseract_log_output(stdout, input_file):
tlog = TesseractLoggerAdapter(
log, extra=log.extra if hasattr(log, 'extra') else None
)
try:
@@ -204,28 +206,28 @@ def tesseract_log_output(mainlog, stdout, input_file):
elif line.startswith("Warning in pixReadMem"):
continue
elif 'diacritics' in line:
log.warning("lots of diacritics - possibly poor OCR")
tlog.warning("lots of diacritics - possibly poor OCR")
elif line.startswith('OSD: Weak margin'):
log.warning("unsure about page orientation")
tlog.warning("unsure about page orientation")
elif 'Error in pixScanForForeground' in line:
pass # Appears to be spurious/problem with nonwhite borders
elif 'Error in boxClipToRectangle' in line:
pass # Always appears with pixScanForForeground message
elif 'parameter not found: ' in line.lower():
log.error(line.strip())
tlog.error(line.strip())
problem = line.split('found: ')[1]
raise TesseractConfigError(problem)
elif 'error' in line.lower() or 'exception' in line.lower():
log.error(line.strip())
tlog.error(line.strip())
elif 'warning' in line.lower():
log.warning(line.strip())
tlog.warning(line.strip())
elif 'read_params_file' in line.lower():
log.error(line.strip())
tlog.error(line.strip())
else:
log.info(line.strip())
tlog.info(line.strip())
def page_timedout(log, input_file, timeout):
def page_timedout(input_file, timeout):
if timeout == 0:
return
prefix = f"{(page_number(input_file)):4d}: [tesseract] "
@@ -257,7 +259,6 @@ def generate_hocr(
user_words,
user_patterns,
tesseract_env,
log,
):
output_hocr = next(o for o in output_files if fspath(o).endswith('.hocr'))
@@ -292,17 +293,17 @@ def generate_hocr(
# Generate a HOCR file with no recognized text if tesseract times out
# Temporary workaround to hocrTransform not being able to function if
# it does not have a valid hOCR file.
page_timedout(log, input_file, timeout)
page_timedout(input_file, timeout)
_generate_null_hocr(output_hocr, output_sidecar, input_file)
except CalledProcessError as e:
tesseract_log_output(log, e.output, input_file)
tesseract_log_output(e.output, input_file)
if b'Image too large' in e.output:
_generate_null_hocr(output_hocr, output_sidecar, input_file)
return
raise SubprocessOutputError() from e
else:
tesseract_log_output(log, stdout, input_file)
tesseract_log_output(stdout, input_file)
# The sidecar text file will get the suffix .txt; rename it to
# whatever caller wants it named
if os.path.exists(prefix + '.txt'):
@@ -340,7 +341,6 @@ def generate_pdf(
user_words,
user_patterns,
tesseract_env,
log,
):
"""Use Tesseract to render a PDF.
@@ -389,13 +389,13 @@ def generate_pdf(
if os.path.exists(prefix + '.txt'):
shutil.move(prefix + '.txt', output_text)
except TimeoutExpired:
page_timedout(log, input_image, timeout)
page_timedout(input_image, timeout)
use_skip_page(text_only, skip_pdf, output_pdf, output_text)
except CalledProcessError as e:
tesseract_log_output(log, e.output, input_image)
tesseract_log_output(e.output, input_image)
if b'Image too large' in e.output:
use_skip_page(text_only, skip_pdf, output_pdf, output_text)
return
raise SubprocessOutputError() from e
else:
tesseract_log_output(log, stdout, input_image)
tesseract_log_output(stdout, input_image)
src/ocrmypdf/exec/unpaper.py
+6 -3
View File
@@ -20,6 +20,7 @@
"""Interface to unpaper executable"""
import logging
import os
import shlex
from functools import lru_cache
@@ -32,13 +33,15 @@ from ..exceptions import MissingDependencyError, SubprocessOutputError
from . import get_version
from . import run as external_run
log = logging.getLogger(__name__)
@lru_cache(maxsize=1)
def version():
return get_version('unpaper')
def run(input_file, output_file, dpi, log, mode_args):
def run(input_file, output_file, dpi, mode_args):
args_unpaper = ['unpaper', '-v', '--dpi', str(dpi)] + mode_args
SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
@@ -110,7 +113,7 @@ def validate_custom_args(args: str):
return unpaper_args
def clean(input_file, output_file, dpi, log, unpaper_args=None):
def clean(input_file, output_file, dpi, unpaper_args=None):
default_args = [
'--layout',
'none',
@@ -124,4 +127,4 @@ def clean(input_file, output_file, dpi, log, unpaper_args=None):
]
if not unpaper_args:
unpaper_args = default_args
run(input_file, output_file, dpi, log, unpaper_args)
run(input_file, output_file, dpi, unpaper_args)