qa/document_analyser.py | 158 ++++++++++++++++++++++++------------------------
1 file changed, 79 insertions(+), 79 deletions(-)
New commits:
commit 579b7d79ac016f8947994a53a9d1ed11869901d6
Author: Xisco Fauli <xiscofa...@libreoffice.org>
AuthorDate: Fri Sep 24 10:42:02 2021 +0200
Commit: Xisco Fauli <xiscofa...@libreoffice.org>
CommitDate: Fri Sep 24 10:52:20 2021 +0200
fix ‘python3\r’: No such file or directory and ...
... remove trailing whitespaces
Change-Id: I5a0b0bbf05ba0c72ccaf36dd9d541730b1698e72
diff --git a/qa/document_analyser.py b/qa/document_analyser.py
old mode 100644
new mode 100755
index 06bc98a..206c573
--- a/qa/document_analyser.py
+++ b/qa/document_analyser.py
@@ -1,79 +1,79 @@
-#!/usr/bin/env python3
-#
-# This file is part of the LibreOffice project.
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at https://mozilla.org/MPL/2.0/.
-#
-
-"""
-Document analyser uses the odfpy module: https://pypi.org/project/odfpy/
-
-This script prints:
-bookmark count, cell count, changetracking count, character count,
-comment count, draw count, frame count, hyperlink count,
-image count, non-whitespace character count, object count, OLE object count,
-page count, paragraph count, row count, sentence count,
-syllable count, table count, textbox count, word count, and paragraph styles.
-
-"""
-
-import odf
-from odf.namespaces import TEXTNS
-from odf.element import Element
-from odf.opendocument import load
-from odf import text,meta,office,draw
-
-
-print("Enter filename: ")
-filename=input()
-
-doc=load(filename)
-
-#--------------------document statistics from the odf.meta
module--------------------
-print("\nDOCUMENT STATISTICS\n")
-for stat in doc.getElementsByType(meta.DocumentStatistic):
- print("Cell count",stat.getAttribute('cellcount'))
- print("Character count:",stat.getAttribute('charactercount'))
- print("Draw count:",stat.getAttribute('drawcount'))
- print("Frame count:",stat.getAttribute('framecount'))
- print("Image count:",stat.getAttribute('imagecount'))
- print("Non-whitespace character
count:",stat.getAttribute('nonwhitespacecharactercount'))
- print("Object count:",stat.getAttribute('objectcount'))
- print("Object linking and embedding (OLE) object
count:",stat.getAttribute('oleobjectcount'))
- print("Page count:",stat.getAttribute('pagecount'))
- print("Paragraph count:",stat.getAttribute('paragraphcount'))
- print("Row count:",stat.getAttribute('rowcount'))
- print("Sentence count:",stat.getAttribute('sentencecount'))
- print("Syllable count:",stat.getAttribute('syllablecount'))
- print("Table count:",stat.getAttribute('tablecount'))
- print("Word count:",stat.getAttribute('wordcount'))
-
-
-#--------------------type counter for attributes not covered by
odf.meta.DocumentStatistic--------------------
-def type_counter(doc,type):
- count=0
- for element in doc.getElementsByType(type):
- count+=1
- return count
-
-types={
- 'Bookmark':text.Bookmark,
- 'Changetracking':text.FormatChange,
- 'Comment':office.Annotation,
- 'Hyperlink':text.A,
- 'Textbox':draw.TextBox
-}
-
-for key,value in types.items():
- print(key,'count:',type_counter(doc,value))
-
-#--------------------paragraph styles--------------------
-def paragraph_style(doc):
- i = 1
- for paragraph in doc.getElementsByType(text.P):
- print('Paragraph',i,'style:',paragraph.getAttribute('stylename'))
- i+=1
-
-paragraph_style(doc)
+#!/usr/bin/env python3
+#
+# This file is part of the LibreOffice project.
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at https://mozilla.org/MPL/2.0/.
+#
+
+"""
+Document analyser uses the odfpy module: https://pypi.org/project/odfpy/
+
+This script prints:
+bookmark count, cell count, changetracking count, character count,
+comment count, draw count, frame count, hyperlink count,
+image count, non-whitespace character count, object count, OLE object count,
+page count, paragraph count, row count, sentence count,
+syllable count, table count, textbox count, word count, and paragraph styles.
+
+"""
+
+import odf
+from odf.namespaces import TEXTNS
+from odf.element import Element
+from odf.opendocument import load
+from odf import text,meta,office,draw
+
+
+print("Enter filename: ")
+filename=input()
+
+doc=load(filename)
+
+#--------------------document statistics from the odf.meta
module--------------------
+print("\nDOCUMENT STATISTICS\n")
+for stat in doc.getElementsByType(meta.DocumentStatistic):
+ print("Cell count",stat.getAttribute('cellcount'))
+ print("Character count:",stat.getAttribute('charactercount'))
+ print("Draw count:",stat.getAttribute('drawcount'))
+ print("Frame count:",stat.getAttribute('framecount'))
+ print("Image count:",stat.getAttribute('imagecount'))
+ print("Non-whitespace character
count:",stat.getAttribute('nonwhitespacecharactercount'))
+ print("Object count:",stat.getAttribute('objectcount'))
+ print("Object linking and embedding (OLE) object
count:",stat.getAttribute('oleobjectcount'))
+ print("Page count:",stat.getAttribute('pagecount'))
+ print("Paragraph count:",stat.getAttribute('paragraphcount'))
+ print("Row count:",stat.getAttribute('rowcount'))
+ print("Sentence count:",stat.getAttribute('sentencecount'))
+ print("Syllable count:",stat.getAttribute('syllablecount'))
+ print("Table count:",stat.getAttribute('tablecount'))
+ print("Word count:",stat.getAttribute('wordcount'))
+
+
+#--------------------type counter for attributes not covered by
odf.meta.DocumentStatistic--------------------
+def type_counter(doc,type):
+ count=0
+ for element in doc.getElementsByType(type):
+ count+=1
+ return count
+
+types={
+ 'Bookmark':text.Bookmark,
+ 'Changetracking':text.FormatChange,
+ 'Comment':office.Annotation,
+ 'Hyperlink':text.A,
+ 'Textbox':draw.TextBox
+}
+
+for key,value in types.items():
+ print(key,'count:',type_counter(doc,value))
+
+#--------------------paragraph styles--------------------
+def paragraph_style(doc):
+ i = 1
+ for paragraph in doc.getElementsByType(text.P):
+ print('Paragraph',i,'style:',paragraph.getAttribute('stylename'))
+ i+=1
+
+paragraph_style(doc)
