New style reader (#1)

chfw · web-flow · commit 8cd5f37b1a1e · 2020-10-02T22:50:00.000+01:00
* 🎉 new style io

* 📚 update readme

* 🤝 update project meta data

* 💄 update coding style

* 📚 update change log and version. 🔥 remove builds lower than python 3.6

* 🔥 remove unwanted matrix
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.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
diff --git a/.github/workflows/moban-update.yml b/.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
diff --git a/.github/workflows/pythonpublish.yml b/.github/workflows/pythonpublish.yml
@@ -0,0 +1,26 @@
+name: Upload Python Package
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v1
+      - name: Set up Python
+        uses: actions/setup-python@v1
+        with:
+          python-version: '3.x'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install setuptools wheel twine
+      - name: Build and publish
+        env:
+          TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+          TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        run: |
+          python setup.py sdist bdist_wheel
+          twine upload dist/*
diff --git a/.gitignore b/.gitignore
@@ -540,3 +540,7 @@ cscope.files
 cscope.out
 cscope.in.out
 cscope.po.out
+
+
+# remove moban hash dictionary
+.moban.hashes
diff --git a/.isort.cfg b/.isort.cfg
@@ -0,0 +1,10 @@
+[settings]
+line_length=79
+known_first_party=pyexcel_io,html5lib
+known_third_party=mock,nose,pyexcel
+indent='    '
+multi_line_output=3
+length_sort=1
+default_section=FIRSTPARTY
+no_lines_before=LOCALFOLDER
+sections=FUTURE,STDLIB,FIRSTPARTY,THIRDPARTY,LOCALFOLDER
diff --git a/.moban.d/custom_travis.yml.jj2 b/.moban.d/custom_travis.yml.jj2
@@ -0,0 +1,8 @@
+{% extends "travis.yml.jj2" %}
+
+{%block custom_python_versions%}
+python:
+  - 3.8
+  - 3.7
+  - 3.6
+{%endblock%}
diff --git a/.moban.yml b/.moban.yml
@@ -2,12 +2,11 @@ overrides: "git://github.com/pyexcel/pyexcel-mobans!/mobanfile.yaml"
 configuration:
   configuration: pyexcel-htmlr.yml
 targets:
-  - README.rst: custom_README.rst.jj2
   - setup.py: custom_setup.py.jj2
   - requirements.txt: requirements.txt
   - MANIFEST.in: MANIFEST.in.jj2
   - "tests/requirements.txt": "tests/custom_requirements.txt.jj2"
-  - .travis.yml: travis.yml.jj2
+  - .travis.yml: custom_travis.yml.jj2
   - .gitignore: gitignore.jj2
   - "docs/source/conf.py": "docs/source/conf.py.jj2"
   - "docs/source/index.rst": "index.rst.jj2"
diff --git a/.travis.yml b/.travis.yml
@@ -4,13 +4,9 @@ language: python
 notifications:
   email: false
 python:
-  - &pypy2 pypy2.7-6.0
-  - &pypy3 pypy3.5-6.0
   - 3.8
   - 3.7
   - 3.6
-  - 3.5
-  - 2.7
 
 stages:
   - lint
@@ -32,7 +28,7 @@ stages:
   env:
     - MINREQ=0
   stage: moban
-  install: pip install moban>=0.0.4 gitfs2 pypifs
+  install: pip install moban gitfs2 pypifs moban-jinja2-github moban-ansible
   script:
     - moban
     - git diff --exit-code
diff --git a/CHANGELOG.rst b/CHANGELOG.rst
@@ -1,6 +1,13 @@
 Change log
 ================================================================================
 
+0.6.0 - tbd
+--------------------------------------------------------------------------------
+
+**Updated**
+
+#. New style xlsx plugins, promoted by pyexcel-io v0.6.0.
+
 0.5.2 - 23.10.2017
 --------------------------------------------------------------------------------
 
diff --git a/CONTRIBUTORS.rst b/CONTRIBUTORS.rst
@@ -0,0 +1,6 @@
+
+
+No contributors yet
+=======================
+
+* Your github link will be listed here after your PR is merged
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -1,5 +1,6 @@
 include README.rst
 include LICENSE
 include CHANGELOG.rst
+include CONTRIBUTORS.rst
 recursive-include tests *
 recursive-include docs *
diff --git a/Makefile b/Makefile
@@ -1,10 +1,16 @@
 all: test
 
-test:
+test: lint
 	bash test.sh
 
-document:
-	bash document.sh
+install_test:
+	pip install -r tests/requirements.txt
 
-spelling:
-	sphinx-build -b spelling docs/source/ docs/build/spelling
+lint:
+	bash lint.sh
+
+format:
+	bash format.sh
+
+git-diff-check:
+	git diff --exit-code
diff --git a/README.rst b/README.rst
@@ -91,6 +91,9 @@ As a standalone library
     ...      from ordereddict import OrderedDict
     ... else:
     ...     from collections import OrderedDict
+    >>> import pyexcel as pe
+    >>> book_data = {"Sheet 1": [[1, 2, 3], [4, 5, 6]], "Sheet 2": [["row 1", "row 2", "row 3"]]}
+    >>> pe.save_book_as(bookdict=book_data, dest_file_name="your_file.html")
 
 
 Read from an html file
@@ -104,7 +107,7 @@ Here's the sample code:
     >>> data = get_data("your_file.html")
     >>> import json
     >>> print(json.dumps(data))
-    {"Sheet 1": [[1, 2, 3], [4, 5, 6]], "Sheet 2": [["row 1", "row 2", "row 3"]]}
+    {"Table 1": [[1, 2, 3], [4, 5, 6]], "Table 2": [["row 1", "row 2", "row 3"]]}
 
 
 
@@ -119,10 +122,11 @@ Continue from previous example:
     >>> # This is just an illustration
     >>> # In reality, you might deal with html file upload
     >>> # where you will read from requests.FILES['YOUR_HTML_FILE']
-    >>> data = get_data(io)
+    >>> with open('your_file.html', 'r') as html_file:
+    ...    io = StringIO(html_file.read().encode())
+    ...    data = get_data(io)
     >>> print(json.dumps(data))
-    {"Sheet 1": [[1, 2, 3], [4, 5, 6]], "Sheet 2": [[7, 8, 9], [10, 11, 12]]}
-
+    {"Table 1": [[1, 2, 3], [4, 5, 6]], "Table 2": [["row 1", "row 2", "row 3"]]}
 
 Pagination feature
 ********************************************************************************
@@ -142,25 +146,25 @@ Let's assume the following file is a huge html file:
    ...     [6, 26, 36]
    ... ]
    >>> sheetx = {
-   ...     "huge": huge_data
+   ...     "Table 1": huge_data
    ... }
-   >>> save_data("huge_file.html", sheetx)
+   >>> pe.save_book_as(dest_file_name="huge_file.html", bookdict=sheetx)
 
 And let's pretend to read partial data:
 
 .. code-block:: python
 
    >>> partial_data = get_data("huge_file.html", start_row=2, row_limit=3)
    >>> print(json.dumps(partial_data))
-   {"huge": [[3, 23, 33], [4, 24, 34], [5, 25, 35]]}
+   {"Table 1": [[3, 23, 33], [4, 24, 34], [5, 25, 35]]}
 
 And you could as well do the same for columns:
 
 .. code-block:: python
 
    >>> partial_data = get_data("huge_file.html", start_column=1, column_limit=2)
    >>> print(json.dumps(partial_data))
-   {"huge": [[21, 31], [22, 32], [23, 33], [24, 34], [25, 35], [26, 36]]}
+   {"Table 1": [[21, 31], [22, 32], [23, 33], [24, 34], [25, 35], [26, 36]]}
 
 Obvious, you could do both at the same time:
 
@@ -170,7 +174,7 @@ Obvious, you could do both at the same time:
    ...     start_row=2, row_limit=3,
    ...     start_column=1, column_limit=2)
    >>> print(json.dumps(partial_data))
-   {"huge": [[23, 33], [24, 34], [25, 35]]}
+   {"Table 1": [[23, 33], [24, 34], [25, 35]]}
 
 .. testcode::
    :hide:
@@ -196,13 +200,13 @@ Here is the sample code:
     >>> import pyexcel as pe
     >>> sheet = pe.get_book(file_name="your_file.html")
     >>> sheet
-    Sheet 1:
+    Table 1:
     +---+---+---+
     | 1 | 2 | 3 |
     +---+---+---+
     | 4 | 5 | 6 |
     +---+---+---+
-    Sheet 2:
+    Table 2:
     +-------+-------+-------+
     | row 1 | row 2 | row 3 |
     +-------+-------+-------+
@@ -220,19 +224,19 @@ You got to wrap the binary content with stream to get html working:
     >>> # This is just an illustration
     >>> # In reality, you might deal with html file upload
     >>> # where you will read from requests.FILES['YOUR_HTML_FILE']
-    >>> htmlfile = "another_file.html"
+    >>> htmlfile = "your_file.html"
     >>> with open(htmlfile, "rb") as f:
     ...     content = f.read()
     ...     r = pe.get_book(file_type="html", file_content=content)
     ...     print(r)
     ...
-    Sheet 1:
+    Table 1:
     +---+---+---+
     | 1 | 2 | 3 |
     +---+---+---+
     | 4 | 5 | 6 |
     +---+---+---+
-    Sheet 2:
+    Table 2:
     +-------+-------+-------+
     | row 1 | row 2 | row 3 |
     +-------+-------+-------+
@@ -320,4 +324,3 @@ What is .moban.d
 
    >>> import os
    >>> os.unlink("your_file.html")
-   >>> os.unlink("another_file.html")
diff --git a/changelog.yml b/changelog.yml
@@ -1,4 +1,10 @@
 releases:
+- changes:
+  - action: Updated
+    details:
+    - 'New style xlsx plugins, promoted by pyexcel-io v0.6.0.'
+  date: tbd
+  version: 0.6.0
 - changes:
   - action: updated
     details:
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -23,9 +23,9 @@
 
 project = 'pyexcel-htmlr'
 copyright = '2015-2019 Onni Software Ltd.'
-author = 'C.W.'
+author = 'chfw'
 # The short X.Y version
-version = '0.5.2'
+version = '0.6.0'
 # The full version, including alpha/beta/rc tags
 release = '0.5.2'
 
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -1,10 +1,11 @@
 `pyexcel-htmlr` - Let you focus on data, instead of file formats
 ================================================================================
 
-:Author: C.W.
+:Author: chfw
 :Source code: http://github.com/pyexcel/pyexcel-htmlr.git
 :Issues: http://github.com/pyexcel/pyexcel-htmlr/issues
 :License: New BSD License
+:Development: |release|
 :Released: |version|
 :Generated: |today|
 
diff --git a/lint.sh b/lint.sh
@@ -1,2 +1,2 @@
 pip install flake8
-flake8 . --exclude=.moban.d,docs,setup.py --builtins=unicode,xrange,long
+flake8 --exclude=.moban.d,docs,setup.py   --builtins=unicode,xrange,long . && python setup.py checkdocs
diff --git a/pyexcel-htmlr.yml b/pyexcel-htmlr.yml
@@ -1,12 +1,15 @@
 overrides: "pyexcel.yaml"
 name: "pyexcel-htmlr"
 nick_name: "htmlr"
-version: "0.5.2"
-current_version: "0.5.2"
+version: "0.6.0"
+current_version: "0.6.0"
 release: "0.5.2"
 file_type: 'html'
 dependencies:
   - html5lib
   - lxml
   - pyexcel-io>=0.5.3
+test_dependencies:
+  - pyexcel-text
+  - pyexcel
 description: "read tables in html file as excel data"
diff --git a/pyexcel_htmlr/__init__.py b/pyexcel_htmlr/__init__.py
diff --git a/pyexcel_htmlr/_version.py b/pyexcel_htmlr/_version.py
diff --git a/pyexcel_htmlr/htmlr.py b/pyexcel_htmlr/htmlr.py
diff --git a/setup.py b/setup.py
diff --git a/tests/requirements.txt b/tests/requirements.txt
diff --git a/tests/test_htmlr.py b/tests/test_htmlr.py
