Merge pull request #7 from pyexcel/dev

release 0.6.0

Author: chfw

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,12 +1,9 @@
 With your PR, here is a check list:
 
-- [ ] Has Test cases written
-- [ ] Has all code lines tested
+- [ ] Has test cases written?
+- [ ] Has all code lines tested?
 - [ ] Has `make format` been run?
-- [ ] Has `moban` been run?
+- [ ] Please update CHANGELOG.yml(not CHANGELOG.rst)
 - [ ] Passes all Travis CI builds
 - [ ] Has fair amount of documentation if your change is complex
-- [ ] run 'make format' so as to confirm the pyexcel organisation's coding style
-- [ ] Please update CHANGELOG.rst
-- [ ] Please add yourself to CONTRIBUTORS.rst
 - [ ] Agree on NEW BSD License for your contribution

.github/workflows/moban-update.yml

@@ -0,0 +1,29 @@
+on: [push]
+
+jobs:
+  run_moban:
+    runs-on: ubuntu-latest
+    name: synchronize templates via moban
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          ref: ${{ github.head_ref }}
+      - name: Set up Python
+        uses: actions/setup-python@v1
+        with:
+          python-version: '3.7'
+      - name: check changes
+        run: |
+          pip install moban gitfs2 pypifs moban-jinja2-github moban-ansible
+          moban
+          git status
+          git diff --exit-code
+      - name: Auto-commit
+        if: failure()
+        uses: docker://cdssnc/auto-commit-github-action
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          args: >-
+            This is an auto-commit, updating project meta data,
+            such as changelog.rst, contributors.rst

.isort.cfg

@@ -0,0 +1,10 @@
+[settings]
+line_length=79
+known_first_party=lxml, pyexcel_io, pyexcel
+known_third_party=mock,nose
+indent='    '
+multi_line_output=3
+length_sort=1
+default_section=FIRSTPARTY
+no_lines_before=LOCALFOLDER
+sections=FUTURE,STDLIB,FIRSTPARTY,THIRDPARTY,LOCALFOLDER

CHANGELOG.rst

@@ -1,6 +1,13 @@
 Change log
 ================================================================================
 
+0.6.0 - 10.10.2020
+--------------------------------------------------------------------------------
+
+**Updated**
+
+#. New style xlsx plugins, promoted by pyexcel-io v0.6.2.
+
 0.5.3 - 23.06.2020
 --------------------------------------------------------------------------------
 

CONTRIBUTORS.rst

@@ -0,0 +1,6 @@
+
+
+No contributors yet
+=======================
+
+* Your github link will be listed here after your PR is merged

LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2015-2019 by Onni Software Ltd. and its contributors
+Copyright (c) 2015-2020 by Onni Software Ltd. and its contributors
 All rights reserved.
 
 Redistribution and use in source and binary forms of the software as well
@@ -13,7 +13,7 @@ that the following conditions are met:
   and/or other materials provided with the distribution.
 
 * Neither the name of 'pyexcel-xlsxr' nor the names of the contributors
-  may be used to endorse or promote products derived from this software
+  may not be used to endorse or promote products derived from this software
   without specific prior written permission.
 
 THIS SOFTWARE AND DOCUMENTATION IS PROVIDED BY THE COPYRIGHT HOLDERS AND

Makefile

@@ -6,9 +6,6 @@ test: lint
 install_test:
 	pip install -r tests/requirements.txt
 
-git-diff-check:
-	git diff --exit-code
-
 lint:
 	bash lint.sh
 

README.rst

@@ -25,6 +25,11 @@ pyexcel-xlsxr - Let you focus on data, instead of xlsx format
 .. image:: https://img.shields.io/gitter/room/gitterHQ/gitter.svg
    :target: https://gitter.im/pyexcel/Lobby
 
+.. image:: https://img.shields.io/static/v1?label=continuous%20templating&message=%E6%A8%A1%E7%89%88%E6%9B%B4%E6%96%B0&color=blue&style=flat-square
+    :target: https://moban.readthedocs.io/en/latest/#at-scale-continous-templating-for-open-source-projects
+
+.. image:: https://img.shields.io/static/v1?label=coding%20style&message=black&color=black&style=flat-square
+    :target: https://github.com/psf/black
 
 **pyexcel-xlsxr** is a specialized xlsx reader using lxml. It does partial reading, meaning
 it wont load all content into memory.
@@ -343,22 +348,6 @@ Please run::
 so as to beautify your code otherwise travis-ci may fail your unit test.
 
 
-And make sure you would have run moban command
----------------------------------------------------------
-
-Additional steps are required:
-
-#. pip install moban
-#. make your changes in `.moban.d` directory, then issue command `moban`
-#. moban
-
-otherwise travis-ci may also fail your unit test.
-
-What is .moban.d
----------------------------------
-
-`.moban.d` stores the specific meta data for the library.
-
 
 .. testcode::
    :hide:

changelog.yml

@@ -1,6 +1,12 @@
 name: pyexcel-xlsxr
 organisation: pyexcel
 releases:
+- changes:
+  - action: Updated
+    details:
+    - 'New style xlsx plugins, promoted by pyexcel-io v0.6.2.'
+  date: 10.10.2020
+  version: 0.6.0
 - changes:
   - action: Fixed
     details:

format.sh

@@ -1,3 +1,3 @@
-isort -y $(find pyexcel_xlsxr -name "*.py"|xargs echo) $(find tests -name "*.py"|xargs echo)
+isort $(find pyexcel_xlsxr -name "*.py"|xargs echo) $(find tests -name "*.py"|xargs echo)
 black -l 79 pyexcel_xlsxr
 black -l 79 tests

lint.sh

@@ -1,3 +1,2 @@
 pip install flake8
-flake8 . --exclude=.moban.d,docs,setup.py --builtins=unicode,xrange,long
-python setup.py checkdocs
+flake8 --exclude=.moban.d,docs,setup.py   --builtins=unicode,xrange,long . && python setup.py checkdocs

pyexcel-xlsxr.yml

@@ -1,15 +1,17 @@
 overrides: "pyexcel.yaml"
 name: "pyexcel-xlsxr"
 nick_name: "xlsxr"
-version: "0.5.3"
-current_version: "0.5.3"
-release: "0.5.3"
+version: "0.6.0"
+current_version: "0.6.0"
+release: "0.6.0"
 file_type: xlsx
 nodocs: true
 dependencies:
-  - lxml >= 3.4.4
-  - pyexcel-io >= 0.5.4
+  - lxml>=3.4.4
+  - pyexcel-io>=0.6.2
 description: "Read xlsx file using partial xml"
 test_dependencies:
-  - pyexcel<=0.6.0
+  - pyexcel
   - pyexcel-xlsxw
+python_requires: ">=3.6"
+min_python_version: "3.6"

pyexcel_xlsxr/__init__.py

@@ -2,19 +2,24 @@
     pyexcel_xlsxr
     ~~~~~~~~~~~~~~~~~~~
     The lower level xlsx file format handler using lxml
-    :copyright: (c) 2015-2017 by Onni Software Ltd & its contributors
+    :copyright: (c) 2015-2020 by Onni Software Ltd & its contributors
     :license: New BSD License
 """
 from pyexcel_io.io import get_data as read_data
 from pyexcel_io.io import isstream
-from pyexcel_io.plugins import IOPluginInfoChain
-
-from pyexcel_xlsxr._version import __author__, __version__  # flake8: noqa
+from pyexcel_io.plugins import IOPluginInfoChainV2
+from pyexcel_xlsxr._version import __author__, __version__  # noqa
 
 __FILE_TYPE__ = "xlsx"
 
-IOPluginInfoChain(__name__).add_a_reader(
+IOPluginInfoChainV2(__name__).add_a_reader(
     relative_plugin_class_path="xlsxr.XLSXBook",
+    locations=["file", "memory"],
+    file_types=[__FILE_TYPE__],
+    stream_type="binary",
+).add_a_reader(
+    relative_plugin_class_path="xlsxr.XLSXBookInContent",
+    locations=["content"],
     file_types=[__FILE_TYPE__],
     stream_type="binary",
 )

pyexcel_xlsxr/_version.py

@@ -1,2 +1,2 @@
-__version__ = "0.5.3"
-__author__ = "C.W."
+__version__ = '0.6.0'
+__author__ = 'chfw'

pyexcel_xlsxr/messy_xlsx.py

@@ -1,7 +1,7 @@
 import io
 import re
 import zipfile
-from datetime import datetime, time, timedelta
+from datetime import time, datetime, timedelta
 
 from lxml import etree
 from pyexcel_io._compact import OrderedDict
@@ -11,15 +11,15 @@
 WORK_BOOK = "xl/workbook.xml"
 SHEET_MATCHER = "xl/worksheets/(work)?sheet([0-9]+)?.xml"
 SHEET_INDEX_MATCHER = "xl/worksheets/(work)?sheet(([0-9]+)?).xml"
-XLSX_ROW_MATCH = re.compile(b".*?(<row.*?<\/.*?row>).*?", re.MULTILINE)
+XLSX_ROW_MATCH = re.compile(rb".*?(<row.*?<\/.*?row>).*?", re.MULTILINE)
 NUMBER_FMT_MATCHER = re.compile(
-    b".*?(<numFmts.*?<\/.*?numFmts>).*?", re.MULTILINE
+    rb".*?(<numFmts.*?<\/.*?numFmts>).*?", re.MULTILINE
 )
 XFS_FMT_MATCHER = re.compile(
-    b".*?(<cellXfs.*?<\/.*?cellXfs>).*?", re.MULTILINE
+    rb".*?(<cellXfs.*?<\/.*?cellXfs>).*?", re.MULTILINE
 )
-SHEET_FMT_MATCHER = re.compile(b".*?(<sheet .*?\/>).*?", re.MULTILINE)
-DATE_1904_MATCHER = re.compile(b".*?(<workbookPr.*?\/>).*?", re.MULTILINE)
+SHEET_FMT_MATCHER = re.compile(rb".*?(<sheet .*?\/>).*?", re.MULTILINE)
+DATE_1904_MATCHER = re.compile(rb".*?(<workbookPr.*?\/>).*?", re.MULTILINE)
 # "xmlns:x14ac="http://schemas.microsoft.com/office/spreadsheetml/2009/9/ac"
 # But it not used for now
 X14AC_NAMESPACE = b'xmlns:x14ac="http://not.used.com/"'
@@ -140,8 +140,9 @@ def __extract_book_properties(self):
         book_content = self.zip_file.open(WORK_BOOK).read()
         return parse_book_properties(book_content)
 
-    def __del__(self):
-        self.zip_file.close()
+    def close(self):
+        if self.zip_file:
+            self.zip_file.close()
 
     def make_tables(self):
         sheet_files = find_sheets(self.zip_file.namelist())
@@ -216,9 +217,9 @@ def parse_cell_type(cell):
     cell_type = None
     if cell.style_string:
         date_time_flag = (
-            re.match("^\d+(\.\d+)?$", cell.value)
+            re.match(r"^\d+(\.\d+)?$", cell.value)
             and re.match(".*[hsmdyY]", cell.style_string)
-            and not re.match(".*\[.*[dmhys].*\]", cell.style_string)
+            and not re.match(r".*\[.*[dmhys].*\]", cell.style_string)
         )
         if cell.style_string in FORMATS:
             cell_type = FORMATS[cell.style_string]
@@ -227,7 +228,7 @@ def parse_cell_type(cell):
                 cell_type = "time"
             else:
                 cell_type = "date"
-        elif re.match("^-?\d+(.\d+)?$", cell.value):
+        elif re.match(r"^-?\d+(.\d+)?$", cell.value):
             cell_type = "float"
     return cell_type
 
@@ -313,9 +314,12 @@ def parse_book_properties(book_content):
                     properties["date1904"] = value.lower().strip() == "true"
                 else:
                     properties["date1904"] = False
-    namespaces = {
-        "r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships"  # flake8: noqa
-    }
+
+    ns = (
+        "http://schemas.openxmlformats.org/"
+        + "officeDocument/2006/relationships"
+    )
+    namespaces = {"r": ns}
 
     xlsx_header = u"<wrapper {0}>".format(
         " ".join('xmlns:{0}="{1}"'.format(k, v) for k, v in namespaces.items())