init

e6ac1409 · gaojiuli · 421b4df2 · e6ac1409 · e6ac1409 · e6ac1409
Commit e6ac1409 authored May 26, 2017 by gaojiuli
Show whitespace changes
Inline Side-by-side

Showing with 187 additions and 0 deletions

setup.py setup.py +22 -0

test_tomd.py test_tomd.py +72 -0

tomd.py tomd.py +93 -0

No files found.
--- a/setup.py
+++ b/setup.py
+from setuptools import find_packages, setup
+
+setup(
+    name="tomd",
+    version="0.1.1",
+    description="Convert HTML to Markdown.",
+    author="Gaojiuli",
+    author_email="gaojiuli@aaronsw.com",
+    url='https://github.com/gaojiuli/tomd',
+    classifiers=[
+        'Development Status :: 5 - Production/Stable',
+        'Intended Audience :: Developers',
+        'License :: OSI Approved :: GNU General Public License (GPL)',
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3.5'
+    ],
+    license='GNU GPL 3',
+    packages=find_packages(),
+    py_modules=['tomd'],
+    include_package_data=True,
+    zip_safe=False,
+)
--- a/test_tomd.py
+++ b/test_tomd.py
+from tomd import Tomd
+
+string = """
+<div class="markdown_body"><p>XData</p>
+<p>Github: <a href="https://github.com/gaojiuli/xdata" rel="nofollow">https://github.com/gaojiuli/xdata</a></p>
+<p>一款非常实用的数据验证工具, 通常用于请求数据的验证.</p>
+<h2>Features</h2>
+<ul>
+<li>验证数据一步到位</li>
+<li>容易扩展,容易自定义数据类型以及验证方式</li>
+<li>无第三方依赖</li>
+</ul>
+<h2>Required</h2>
+<ul>
+<li>python &gt;= 3.5</li>
+</ul>
+<h2>Installation</h2>
+<p><code>pip install xdata</code></p>
+<h2>Usage</h2>
+<h3>ValidatedData</h3>
+<pre><code class="hljs python"><span class="hljs-keyword">from</span> xdata <span class="hljs-keyword">import</span> *
+
+<span class="hljs-class"><span class="hljs-keyword">class</span> <span class="hljs-title">UserSchema</span><span class="hljs-params">(Schema)</span>:</span>
+    telephone = Str(length=<span class="hljs-number">11</span>, required=<span class="hljs-keyword">True</span>)
+    password = Str(min_length=<span class="hljs-number">8</span>,max_length=<span class="hljs-number">16</span>, required=<span class="hljs-keyword">True</span>)
+    
+request_data = {
+    <span class="hljs-string">'telephone'</span>:<span class="hljs-string">'18180050000'</span>,
+    <span class="hljs-string">'password'</span>:<span class="hljs-string">'idonotknow'</span>
+}
+
+schema = UserSchema(request_data)
+<span class="hljs-keyword">if</span> schema.valid:
+    print(schema.validated_data) <span class="hljs-comment"># {'telephone': '18180050000', 'password': 'idonotknow'}</span>
+
+</code></pre>
+<h3>Errors</h3>
+<pre><code class="hljs python"><span class="hljs-keyword">from</span> xdata <span class="hljs-keyword">import</span> *
+
+<span class="hljs-class"><span class="hljs-keyword">class</span> <span class="hljs-title">UserSchema</span><span class="hljs-params">(Schema)</span>:</span>
+    telephone = Str(length=<span class="hljs-number">11</span>, required=<span class="hljs-keyword">True</span>)
+    password = Str(min_length=<span class="hljs-number">8</span>, max_length=<span class="hljs-number">16</span>, required=<span class="hljs-keyword">True</span>)
+
+
+request_data = {}
+
+schema = UserSchema(request_data)
+<span class="hljs-keyword">if</span> <span class="hljs-keyword">not</span> schema.valid:
+    print(schema.errors)  <span class="hljs-comment"># {'telephone': 'telephone is required', 'password': 'password is required'}</span>
+</code></pre>
+<h3>DataTypes</h3>
+<pre><code class="hljs lisp">from xdata import *
+
+DataType(<span class="hljs-name">required=True</span>,default='<span class="hljs-number">11</span>',choices=[])
+
+Str(<span class="hljs-name">length=11</span>, max_length=12,min_length=10,regex=<span class="hljs-string">""</span>)
+Int(<span class="hljs-name">max=10000</span>,min=12)
+Bool(<span class="hljs-name">max=10000</span>,min=12)
+Decimal(<span class="hljs-name">left=5</span>,right=2)
+DateTime(<span class="hljs-name">max_datetime=</span>'<span class="hljs-number">2001</span><span class="hljs-number">-01</span><span class="hljs-number">-01</span> <span class="hljs-number">00</span>:<span class="hljs-number">00</span>:<span class="hljs-number">00</span>', min_datetime='<span class="hljs-number">2000</span><span class="hljs-number">-01</span><span class="hljs-number">-01</span> <span class="hljs-number">00</span>:<span class="hljs-number">00</span>:<span class="hljs-number">00</span>')
+Date(<span class="hljs-name">max_date=</span>'<span class="hljs-number">2001</span><span class="hljs-number">-01</span><span class="hljs-number">-01</span>', min_date='<span class="hljs-number">2000</span><span class="hljs-number">-01</span><span class="hljs-number">-01</span>')
+Time(<span class="hljs-name">max_time=</span>'<span class="hljs-number">06</span>:<span class="hljs-number">00</span>:<span class="hljs-number">00</span>', min_time='<span class="hljs-number">05</span>:<span class="hljs-number">00</span>:<span class="hljs-number">00</span>')
+
+</code></pre>
+<h2>Test</h2>
+<p><code>coverage run --source=xdata -m pytest &amp;&amp; coverage report</code></p>
+<p>Github: <a href="https://github.com/gaojiuli/xdata" rel="nofollow">https://github.com/gaojiuli/xdata</a></p>
+<p>欢迎有兴趣的朋友一起参与进来</p>
+</div>
+"""
+# Tomd(string)
+Tomd(string)
--- a/tomd.py
+++ b/tomd.py
+import re
+
+MARKDOWN = {
+    'h1': ('\n# ', '\n'),
+    'h2': ('\n## ', '\n'),
+    'h3': ('\n### ', '\n'),
+    'h4': ('\n#### ', '\n'),
+    'h5': ('\n##### ', '\n'),
+    'h6': ('\n###### ', '\n'),
+    'p': ('\n', '\n'),
+    'p_with_out_class': ('\n', '\n'),
+    'code': ('`', '`'),
+    'ul': ('\n', '\n'),
+    'ol': ('\n', '\n'),
+    'li': ('*. ', ''),
+    'blockquote': ('> ', '\n'),
+    'em': ('**', '**'),
+    'a': ('[](', ')'),
+    'img': ('![](', ')'),
+    'block_code': ('\n```\n', '\n```\n'),
+    'span': ('', '')
+}
+
+BlOCK_ELEMENTS = {
+    'h1': '<h1.*?>(.*?)</h1>',
+    'h2': '<h2.*?>(.*?)</h2>',
+    'h3': '<h3.*?>(.*?)</h3>',
+    'h4': '<h4.*?>(.*?)</h4>',
+    'h5': '<h5.*?>(.*?)</h5>',
+    'h6': '<h6.*?>(.*?)</h6>',
+    'p': '<p\s.*?>(.*?)</p>',
+    'p_with_out_class': '<p>(.*?)</p>',
+    'blockquote': '<blockquote.*?>(.*?)</blockquote>',
+    'ul': '<ul.*?>(.*?)</ul>',
+    'block_code': '<pre.*?><code.*?>(.*?)</code></pre>',
+}
+
+INLINE_ELEMENTS = {
+    'code': '<code.*?>(.*?)</code>',
+    'span': '<span.*?>(.*?)</span>',
+    'ol': '<ol.*?>(.*?)</ol>',
+    'li': '<li.*?>(.*?)</li>',
+    'img': '<img.*?>(.*?)</img>',
+    'a': '<a.*?>(.*?)</a>',
+    'em': '<em.*?>(.*?)</em>',
+    # 'pre': '<pre.*><code.*>(.*)</code></pre>',
+}
+
+
+class Element:
+    def __init__(self, pos, content, tag):
+        self.pos = pos
+        self.content = content
+        self._elements = []
+        self.tag = tag
+        self._result = None
+
+        if tag in BlOCK_ELEMENTS:
+            self.parse_inline()
+
+    def __str__(self):
+        wrapper = MARKDOWN.get(self.tag)
+        self._result = '{}{}{}'.format(wrapper[0], self.content, wrapper[1])
+        return self._result
+
+    def parse_inline(self):
+        for tag, pattern in INLINE_ELEMENTS.items():
+            wrapper = MARKDOWN.get(tag)
+            self.content = re.sub(pattern, '{}\g<1>{}'.format(wrapper[0], wrapper[1]), self.content)
+
+
+class Tomd:
+    def __init__(self, html):
+        self.html = html
+        self._elements = []
+        self._markdown = None
+        self.parse_block()
+        print(self._markdown)
+        for element in self._elements:
+            if len(element._result) > 1000:
+                print(element.__dict__)
+
+    def parse_block(self):
+        for tag, pattern in BlOCK_ELEMENTS.items():
+            for m in re.finditer(pattern, self.html, re.I | re.S | re.M):
+                element = Element(pos=m.start(), content=''.join(m.groups()), tag=tag)
+                self._elements.append(element)
+        self._elements.sort(key=lambda element: element.pos)
+        self._markdown = ''.join([str(e) for e in self._elements])
+
+    @property
+    def markdown(self):
+        return self._markdown