commit 54bbb748fd328e42a01c27fa3a460699a26c8171
parent 306aa78eff53aa02ca8ad892eecd24b9d097a69f
Author: ng0 <ng0@n0.is>
Date: Sat, 2 Dec 2017 13:13:40 +0000
pep
Diffstat:
2 files changed, 92 insertions(+), 94 deletions(-)
diff --git a/examples/extract.py b/examples/extract.py
@@ -31,17 +31,17 @@ import struct
xtract = extractor.Extractor()
+
def print_k(xt, plugin, type, format, mime, data, datalen):
- mstr = cast (data, c_char_p)
-# FIXME: this ignores 'datalen', not that great...
-# (in general, depending on the mime type and format, only
-# the first 'datalen' bytes in 'data' should be used).
+ mstr = cast(data, c_char_p)
+ # FIXME: this ignores 'datalen', not that great...
+ # (in general, depending on the mime type and format, only
+ # the first 'datalen' bytes in 'data' should be used).
if (format == extractor.EXTRACTOR_METAFORMAT_UTF8):
- print("%s - %s" % (xtract.keywordTypes()[type], mstr.value))
+ print("%s - %s" % (xtract.keywordTypes()[type], mstr.value))
return 0
for arg in sys.argv[1:]:
print("Keywords from %s:" % arg)
xtract.extract(print_k, None, arg)
-
diff --git a/libextractor/extractor.py b/libextractor/extractor.py
@@ -1,24 +1,25 @@
# -*- coding: utf-8 -*-
-## Python bindings for GNU libextractor
-##
-## Copyright (C) 2006 Bader Ladjemi <bader@tele2.fr>
-## Copyright (C) 2011 Christian Grothoff <christian@grothoff.org>
-##
-## This program is free software; you can redistribute it and/or modify
-## it under the terms of the GNU General Public License as published by
-## the Free Software Foundation; either version 3 of the License, or
-## (at your option) any later version.
-##
-## This program is distributed in the hope that it will be useful,
-## but WITHOUT ANY WARRANTY; without even the implied warranty of
-## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-## GNU General Public License for more details.
-##
-## You should have received a copy of the GNU General Public License
-## along with this program; see the file COPYING. If not, write to the
-## Free Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139,
-## USA.
-##
+# Python bindings for GNU libextractor
+#
+# Copyright (C) 2006 Bader Ladjemi <bader@tele2.fr>
+# Copyright (C) 2011 Christian Grothoff <christian@grothoff.org>
+# Copyright (C) 2017 ng0 <ng0@n0.is>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; see the file COPYING. If not, write to the
+# Free Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139,
+# USA.
+
"""
Python bindings for GNU libextractor
@@ -27,18 +28,18 @@ does not support all formats but supports a simple plugging mechanism
such that you can quickly add extractors for additional formats, even
without recompiling libextractor. libextractor typically ships with a
dozen helper-libraries that can be used to obtain keywords from common
-file-types.
+file-types.
-libextractor is a part of the GNU project (http://www.gnu.org/).
+libextractor is a part of the GNU project (http://www.gnu.org/).
"""
from ctypes import *
-#fake cdll import
+# fake cdll import
try:
- #loading shared object file
+ # loading shared object file
libextractor = cdll.LoadLibrary('libextractor.so.3')
except OSError:
libextractor = cdll.extractor
-
+
__all__ = ['Extractor']
__version__ = "0.6"
__licence__ = "GNU GPL"
@@ -77,40 +78,40 @@ class Extractor(object):
Use the add and remove libraries methods to change the list of
libraries that should be used.
"""
-
+
def __init__(self, defaults=True, libraries=None):
- """
- Initialize Extractor's instance
-
- @param libraries: list of strings that contains extractor's name (supported types)
- @param defaults: load default plugins
-
- """
- self.extractors = None
- if defaults:
- self.extractors = libextractor.EXTRACTOR_plugin_add_defaults(0)
- if libraries:
- self.extractors = libextractor.EXTRACTOR_plugin_add_config (self.extractors, libraries, 0)
+ """
+ Initialize Extractor's instance
+
+ @param libraries: list of strings that contains extractor's name (supported types)
+ @param defaults: load default plugins
+ """
+ self.extractors = None
+ if defaults:
+ self.extractors = libextractor.EXTRACTOR_plugin_add_defaults(0)
+ if libraries:
+ self.extractors = libextractor.EXTRACTOR_plugin_add_config (self.extractors, libraries, 0)
def extract(self, proc, proc_cls, filename=None, data=None, size=0):
- """Extract keywords from a file, or from its data.
+ """
+ Extract keywords from a file, or from its data.
- @param filename: filename string
- @param data: data contents
- @param size: data size
+ @param filename: filename string
+ @param data: data contents
+ @param size: data size
@param proc: function to call on each value
@param proc_cls: closure to proc
- If you give data, size has to be given as well.
+ If you give data, size has to be given as well.
"""
- if not filename and not (data and size):
- return None
- else:
- libextractor.EXTRACTOR_extract (self.extractors, filename, data, size, EXTRACT_CB(proc), proc_cls)
-
+ if not filename and not (data and size):
+ return None
+ else:
+ libextractor.EXTRACTOR_extract (self.extractors, filename, data, size, EXTRACT_CB(proc), proc_cls)
+
def addLibrary(self, library):
- """
+ """
Add given library to the extractor. Invoke with a string with the name
of the library that should be added. For example,
@@ -122,12 +123,12 @@ class Extractor(object):
No errors are reported if the library is not
found.
- @param library: library's name
+ @param library: library's name
"""
- self.extractors = libextractor.EXTRACTOR_plugin_add (self.extractors, library, NULL, 0)
+ self.extractors = libextractor.EXTRACTOR_plugin_add (self.extractors, library, NULL, 0)
def removeLibrary(self, library):
- """
+ """
Remove a library. Pass the name of the library that is to
be removed. Only one library can be removed at a time.
For example,
@@ -135,58 +136,55 @@ class Extractor(object):
'libextractor_pdf'
removes the PDF extractor (if added).
- ValueError will be thrown if no library match.
+ ValueError will be thrown if no library match.
- @param library: library's name
- """
+ @param library: library's name
+ """
- self.extractors = libextractor.EXTRACTOR_plugin_remove(self.extractors, library)
+ self.extractors = libextractor.EXTRACTOR_plugin_remove(self.extractors, library)
def addLibraries(self, libraries):
- """
- Add given libraries.
- Same as addLibary but libraries is a list of library's names.
+ """
+ Add given libraries.
+ Same as addLibary but libraries is a list of library's names.
- @param libraries: list of libraries names
- """
+ @param libraries: list of libraries names
+ """
- self.extractors = libextractor.EXTRACTOR_plugin_add_config(self.extractors, libraries)
+ self.extractors = libextractor.EXTRACTOR_plugin_add_config(self.extractors, libraries)
def removeAllLibraries(self):
- """
- Remove all libraries.
-
- """
+ """
+ Remove all libraries.
+ """
libextractor.EXTRACTOR_plugin_remove_all(self.extractors)
self.extractors = None
def keywordTypes(self):
- """
- Returns the list of all keywords types.
- @return: list of all keywords types
+ """
+ Returns the list of all keywords types.
+ @return: list of all keywords types
+ """
+ i = 0
+ keyword_types = []
- """
- i = 0
- keyword_types = []
-
- while True:
- keyword_type = libextractor.EXTRACTOR_metatype_to_string(i)
- if not keyword_type:
- break
- keyword_types.append(keyword_type)
- i += 1
-
- return tuple(keyword_types)
-
+ while True:
+ keyword_type = libextractor.EXTRACTOR_metatype_to_string(i)
+ if not keyword_type:
+ break
+ keyword_types.append(keyword_type)
+ i += 1
+
+ return tuple(keyword_types)
def __del__(self):
- """
- >>> extractor = Extractor()
- >>> del extractor
- """
- if self.extractors:
- self.removeAllLibraries()
+ """
+ >>> extractor = Extractor()
+ >>> del extractor
+ """
+ if self.extractors:
+ self.removeAllLibraries()
if __name__ == "__main__":
import doctest
