matthias/mayan-edms
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Use copyfileobj in the document parsers

Browse Source 
Signed-off-by: Roberto Rosario <roberto.rosario.gonzalez@gmail.com>
This commit is contained in:
Roberto Rosario
2019-04-21 03:59:30 -04:00
parent 64cd0c232d
commit 5cfc5dda92
3 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
HISTORY.rst
View File

@@ -95,6 +95,7 @@
* Move the purge permission logic to the StorePermission * Move the purge permission logic to the StorePermission
manager. manager.
* Remove the MIMETYPE_FILE_READ_SIZE setting. * Remove the MIMETYPE_FILE_READ_SIZE setting.
* Use copyfileobj in the document parsers.
3.1.11 (2019-04-XX) 3.1.11 (2019-04-XX)
=================== ===================

1
docs/releases/3.2.rst
View File

@@ -127,6 +127,7 @@ Other changes
* Move the purge permission logic to the StorePermission * Move the purge permission logic to the StorePermission
manager. manager.
* Remove the MIMETYPE_FILE_READ_SIZE setting. * Remove the MIMETYPE_FILE_READ_SIZE setting.
* Use copyfileobj in the document parsers.
Removals Removals
-------- --------

14
mayan/apps/document_parsing/parsers.py
View File

@@ -2,12 +2,13 @@ from __future__ import unicode_literals
import logging import logging
import os import os
from shutil import copyfileobj
import subprocess import subprocess
from django.apps import apps from django.apps import apps
from django.utils.translation import ugettext_lazy as _ from django.utils.translation import ugettext_lazy as _
from mayan.apps.storage.utils import copyfile, fs_cleanup, mkstemp from mayan.apps.storage.utils import NamedTemporaryFile
from .exceptions import ParserError from .exceptions import ParserError
from .settings import setting_pdftotext_path from .settings import setting_pdftotext_path
@@ -123,8 +124,9 @@ class PopplerParser(Parser):
def execute(self, file_object, page_number): def execute(self, file_object, page_number):
logger.debug('Parsing PDF page: %d', page_number) logger.debug('Parsing PDF page: %d', page_number)
destination_descriptor, temp_filepath = mkstemp() temporary_file_object = NamedTemporaryFile()
copyfile(file_object, temp_filepath) copyfileobj(fsrc=file_object, fdst=temporary_file_object)
temporary_file_object.seek(0)
command = [] command = []
command.append(self.pdftotext_path) command.append(self.pdftotext_path)
@@ -132,7 +134,7 @@ class PopplerParser(Parser):
command.append(str(page_number)) command.append(str(page_number))
command.append('-l') command.append('-l')
command.append(str(page_number)) command.append(str(page_number))
command.append(temp_filepath) command.append(temporary_file_object.name)
command.append('-') command.append('-')
proc = subprocess.Popen( proc = subprocess.Popen(
@@ -142,12 +144,12 @@ class PopplerParser(Parser):
return_code = proc.wait() return_code = proc.wait()
if return_code != 0: if return_code != 0:
logger.error(proc.stderr.readline()) logger.error(proc.stderr.readline())
fs_cleanup(temp_filepath, file_descriptor=destination_descriptor) temporary_file_object.close()
raise ParserError raise ParserError
output = proc.stdout.read() output = proc.stdout.read()
fs_cleanup(temp_filepath, file_descriptor=destination_descriptor) temporary_file_object.close()
if output == b'\x0c': if output == b'\x0c':
logger.debug('Parser didn\'t return any output') logger.debug('Parser didn\'t return any output')