v1.48 fixed openpyxl generated read/write errors

PydPiper · Nov 19, 2020 · 759b51a · 759b51a
1 parent 72597ab
commit 759b51a
Show file tree

Hide file tree

Showing 16 changed files with 108 additions and 18 deletions.
diff --git a/README.md b/README.md
@@ -87,18 +87,12 @@ and/or download restrictions, see [docs - installation](https://pylightxl.readth
 
 ---
 
-#### **pypi version 1.47**
-
-- added new function: ``db.nr('table1')`` returns the contents of named range "table1"
-- added new function: ``db.ws('Sheet1').range('A1:C3')`` that returns the contents of a range
-  it also has the ability to return the formulas of the range
-- updated ``db.ws('Sheet1').row()`` and ``db.ws('Sheet1').col()`` to take in a new argument ``formual``
-  that returns the formulas of a row or col
-- bugfix: write to existing without named ranges was throwing a "repair" error. Fixed typo on xml for it
-  and added unit tests to capture it
-- added new function: ``xl.readcsv(fn, delimiter, ws)`` to read csv files and create a pylightxl db out
-  of it (type converted)
-- added new function: ``xl.writecsv(db, fn, ws, delimiter)`` to write out a pylightxl worksheet as a csv
+#### **pypi version 1.48**
+
+- add feature to ``writecsv`` to be able to handle ``pathlib`` object and ``io.StreamIO`` object
+- refactored readxl to remove regex, now readxl is all cElementTree
+- refactored readxl/writexl to able to handle excel files written by openpyxl that is generated 
+  differently than how excel write files. 
 
 See full history log of revisions: [Here](https://pylightxl.readthedocs.io/en/latest/revlog.html)
 

diff --git a/_config.yml b/_config.yml
diff --git a/doc/source/revlog.rst b/doc/source/revlog.rst
@@ -1,10 +1,16 @@
 Revision Log
 ============
 
-pypi version 1.48 (in-work)
+pypi version 1.49 (in-work)
 ---------------------------
+- speed improvements
+
+pypi version 1.48
+-----------------
 - add feature to ``writecsv`` to be able to handle ``pathlib`` object and ``io.StreamIO`` object
 - refactored readxl to remove regex, now readxl is all cElementTree
+- refactored readxl/writexl to able to handle excel files written by openpyxl that is generated
+  differently than how excel write files.
 
 pypi version 1.47
 -----------------

diff --git a/pylightxl/pylightxl.py b/pylightxl/pylightxl.py
@@ -229,6 +229,9 @@ def readxl_get_workbookxmlrels(fn):
 
     for relationship in root.findall('./default:Relationship', ns):
         fn_ws = relationship.get('Target')
+        # openpyxl write its xl/_rels/workbook.xml.rels file differently than excel itself. It adds on /xl/ at the start of the file path
+        if fn_ws[:4] == '/xl/':
+            fn_ws = fn_ws[4:]
         rId = relationship.get('Id')
         rv[rId] = fn_ws
 
@@ -570,7 +573,12 @@ def writexl_alt_app_text(db, filepath):
 
     if db.nr_names == {}:
         # does not contain namedranges
-        tag_vt_vector = root.find('./default:HeadingPairs//vt:vector', ns)
+        try:
+            tag_vt_vector = root.find('./default:HeadingPairs//vt:vector', ns)
+        except SyntaxError:
+            # this occurs when excel file was created by another program like openpyxl
+            # where not all information was written to docProps/app.xml
+            return writexl_new_app_text(db)
         tag_vt_vector.clear()
         tag_vt_vector.set('size', '2')
         tag_vt_vector.set('baseType', 'variant')
@@ -587,10 +595,14 @@ def writexl_alt_app_text(db, filepath):
         tag_vt_lpstr.text = str(len(db.ws_names))
         tag_vt_variant.append(tag_vt_lpstr)
 
-
     else:
         # contains namedranges
-        tag_vt_vector = root.find('./default:HeadingPairs//vt:vector', ns)
+        try:
+            tag_vt_vector = root.find('./default:HeadingPairs//vt:vector', ns)
+        except SyntaxError:
+            # this occurs when excel file was created by another program like openpyxl
+            # where not all information was written to docProps/app.xml
+            return writexl_new_app_text(db)
         tag_vt_vector.clear()
         tag_vt_vector.set('size', '4')
         tag_vt_vector.set('baseType', 'variant')

diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="pylightxl", # Replace with your own username
-    version="1.47",
+    version="1.48",
     author="Viktor Kis",
     author_email="",
     description="A light weight excel read/writer for python27 and python3 with no dependencies",

diff --git a/test/_pylightxl_newopenpyxl.xlsx/[Content_Types].xml b/test/_pylightxl_newopenpyxl.xlsx/[Content_Types].xml
@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
+<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
+<Default Extension="xml" ContentType="application/xml"/>
+<Override PartName="/xl/workbook.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet.main+xml"/>
+<Override PartName="/xl/worksheets/sheet1.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml"/>
+
+
+<Override PartName="/docProps/core.xml" ContentType="application/vnd.openxmlformats-package.core-properties+xml"/>
+<Override PartName="/docProps/app.xml" ContentType="application/vnd.openxmlformats-officedocument.extended-properties+xml"/>
+</Types>

diff --git a/test/_pylightxl_newopenpyxl.xlsx/_rels/.rels b/test/_pylightxl_newopenpyxl.xlsx/_rels/.rels
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+<Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/extended-properties" Target="docProps/app.xml"/>
+<Relationship Id="rId2" Type="http://schemas.openxmlformats.org/package/2006/relationships/metadata/core-properties" Target="docProps/core.xml"/>
+<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="xl/workbook.xml"/>
+</Relationships>
diff --git a/test/_pylightxl_newopenpyxl.xlsx/docProps/app.xml b/test/_pylightxl_newopenpyxl.xlsx/docProps/app.xml
@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Properties xmlns="http://schemas.openxmlformats.org/officeDocument/2006/extended-properties" xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+<Application>Microsoft Excel</Application>
+<DocSecurity>0</DocSecurity>
+<ScaleCrop>false</ScaleCrop>
+<HeadingPairs>
+<vt:vector size="2" baseType="variant"><vt:variant><vt:lpstr>Worksheets</vt:lpstr></vt:variant><vt:variant><vt:i4>1</vt:i4></vt:variant></vt:vector></HeadingPairs>
+<TitlesOfParts>
+<vt:vector size="1" baseType="lpstr"><vt:lpstr>Sheet</vt:lpstr></vt:vector></TitlesOfParts>
+<Company />
+<LinksUpToDate>false</LinksUpToDate>
+<SharedDoc>false</SharedDoc>
+<HyperlinksChanged>false</HyperlinksChanged>
+<AppVersion>16.0300</AppVersion>
+</Properties>
diff --git a/test/_pylightxl_newopenpyxl.xlsx/docProps/core.xml b/test/_pylightxl_newopenpyxl.xlsx/docProps/core.xml
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<cp:coreProperties xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dcmitype="http://purl.org/dc/dcmitype/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties">
+<dc:creator>pylightxl</dc:creator>
+<cp:lastModifiedBy>pylightxl</cp:lastModifiedBy>
+<dcterms:created xsi:type="dcterms:W3CDTF">2019-12-27T01:35:28Z</dcterms:created>
+<dcterms:modified xsi:type="dcterms:W3CDTF">2019-12-27T01:35:39Z</dcterms:modified>
+</cp:coreProperties>
diff --git a/test/_pylightxl_newopenpyxl.xlsx/xl/_rels/workbook.xml.rels b/test/_pylightxl_newopenpyxl.xlsx/xl/_rels/workbook.xml.rels
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+<Relationship Target="worksheets/sheet1.xml" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet" Id="rId1"/>
+
+
+</Relationships>

diff --git a/test/_pylightxl_newopenpyxl.xlsx/xl/sharedStrings.xml b/test/_pylightxl_newopenpyxl.xlsx/xl/sharedStrings.xml
@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<sst uniqueCount="0" count="0" xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+
+</sst>

diff --git a/test/_pylightxl_newopenpyxl.xlsx/xl/workbook.xml b/test/_pylightxl_newopenpyxl.xlsx/xl/workbook.xml
@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<workbook xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" mc:Ignorable="x15 xr xr6 xr10 xr2" xmlns:x15="http://schemas.microsoft.com/office/spreadsheetml/2010/11/main" xmlns:xr="http://schemas.microsoft.com/office/spreadsheetml/2014/revision" xmlns:xr6="http://schemas.microsoft.com/office/spreadsheetml/2016/revision6" xmlns:xr10="http://schemas.microsoft.com/office/spreadsheetml/2016/revision10" xmlns:xr2="http://schemas.microsoft.com/office/spreadsheetml/2015/revision2">
+<fileVersion appName="xl" lastEdited="7" lowestEdited="7" rupBuild="22228"/>
+<workbookPr defaultThemeVersion="166925"/>
+<sheets>
+<sheet name="Sheet" sheetId="1" r:id="rId1"/>
+
+</sheets>
+<calcPr calcId="181029"/>
+</workbook>

diff --git a/test/_pylightxl_newopenpyxl.xlsx/xl/worksheets/sheet1.xml b/test/_pylightxl_newopenpyxl.xlsx/xl/worksheets/sheet1.xml
@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" mc:Ignorable="x14ac xr xr2 xr3" xmlns:x14ac="http://schemas.microsoft.com/office/spreadsheetml/2009/9/ac" xmlns:xr="http://schemas.microsoft.com/office/spreadsheetml/2014/revision" xmlns:xr2="http://schemas.microsoft.com/office/spreadsheetml/2015/revision2" xmlns:xr3="http://schemas.microsoft.com/office/spreadsheetml/2016/revision3" xr:uid="2C7EE24B-C535-494D-AA97-0A61EE84BA40">
+<dimension ref="A1"/>
+<sheetViews>
+<sheetView tabSelected="1" workbookViewId="0"/>
+</sheetViews>
+<sheetFormatPr defaultRowHeight="15" x14ac:dyDescent="0.25"/>
+<sheetData>
+<row r="1" x14ac:dyDescent="0.25" spans="1:1"><c r="A1" ><v>42</v></c></row>
+
+</sheetData>
+<pageMargins left="0.7" right="0.7" top="0.75" bottom="0.75" header="0.3" footer="0.3"/>
+</worksheet>

diff --git a/test/newopenpyxl.xlsx b/test/newopenpyxl.xlsx
diff --git a/test/openpyxl.xlsx b/test/openpyxl.xlsx
diff --git a/test/test_writexl.py b/test/test_writexl.py
@@ -333,6 +333,13 @@ def test_new_content_types_text(self):
         db._sharedStrings = ['text']
         self.assertEqual(xl.writexl_new_content_types_text(db), xml_base.format(many_tag_sheets=many_tag_sheets, tag_sharedStrings=xml_tag_sharedStrings))
 
+    def test_openpyxl(self):
+        # test that pylightxl is able to write to a openpyxl output excel file (docProps/app.xml) is different than expected
+        db = xl.readxl('openpyxl.xlsx')
+
+        xl.writexl(db, 'newopenpyxl.xlsx')
+
+
 
 class TestWritexlExisting(TestCase):