snipt

Ctrl+h for KB shortcuts

Python 3

Strip Javascript comments from string using Regular Expressions

import re

re_js_comments_str = r"""
    (                               # Capture code
        (?:
            "(?:\\.|[^"\\])*"           # String literal
            |
            '(?:\\.|[^'\\])*'           # String literal
            |
            (?:[^/\n"']|/[^/*\n"'])+    # Any code besides newlines or string literals (essentially no comments)
            |
            \n                          # Newline
        )+                          # Repeat
    )|
    (/\* (?:[^*]|\*[^/])* \*/)      # Multi-line comment
    |
    (?://(.*)$)                     # Comment
"""
re_js_comments = re.compile(re_js_comments_str, re.VERBOSE + re.MULTILINE)


def strip_js_comments(string):
    """Originally obtained from Stackoverflow this function strips JavaScript
    (and JSON) comments from a string while considering those encapsulated by strings.

        Source: http://stackoverflow.com/questions/2136363/matching-one-line-javascript-comments-with-re
    """
    parts = re_js_comments.findall(string)
    # Stripping the whitespaces is, of course, optional, but the columns are fucked up anyway
    # with the comments being removed and it doesn't break things.
    return ''.join([x[0].strip(' ') for x in parts])
https://snipt.net/embed/5a48603ccf6418e87f24bf188d7a0312/
/raw/5a48603ccf6418e87f24bf188d7a0312/
5a48603ccf6418e87f24bf188d7a0312
python3
Python 3
32
2019-06-17T08:32:49
True
False
False
Jan 05, 2013 at 07:19 AM
/api/public/snipt/52793/
strip-javascript-comments-from-string-using-regular-expressions
<table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><a href="#L-1"> 1</a> <a href="#L-2"> 2</a> <a href="#L-3"> 3</a> <a href="#L-4"> 4</a> <a href="#L-5"> 5</a> <a href="#L-6"> 6</a> <a href="#L-7"> 7</a> <a href="#L-8"> 8</a> <a href="#L-9"> 9</a> <a href="#L-10">10</a> <a href="#L-11">11</a> <a href="#L-12">12</a> <a href="#L-13">13</a> <a href="#L-14">14</a> <a href="#L-15">15</a> <a href="#L-16">16</a> <a href="#L-17">17</a> <a href="#L-18">18</a> <a href="#L-19">19</a> <a href="#L-20">20</a> <a href="#L-21">21</a> <a href="#L-22">22</a> <a href="#L-23">23</a> <a href="#L-24">24</a> <a href="#L-25">25</a> <a href="#L-26">26</a> <a href="#L-27">27</a> <a href="#L-28">28</a> <a href="#L-29">29</a> <a href="#L-30">30</a> <a href="#L-31">31</a></pre></div></td><td class="code"><div class="highlight"><pre><span></span><span id="L-1"><a name="L-1"></a><span class="kn">import</span> <span class="nn">re</span> </span><span id="L-2"><a name="L-2"></a> </span><span id="L-3"><a name="L-3"></a><span class="n">re_js_comments_str</span> <span class="o">=</span> <span class="s2">r&quot;&quot;&quot;</span> </span><span id="L-4"><a name="L-4"></a><span class="s2"> ( # Capture code</span> </span><span id="L-5"><a name="L-5"></a><span class="s2"> (?:</span> </span><span id="L-6"><a name="L-6"></a><span class="s2"> &quot;(?:\\.|[^&quot;\\])*&quot; # String literal</span> </span><span id="L-7"><a name="L-7"></a><span class="s2"> |</span> </span><span id="L-8"><a name="L-8"></a><span class="s2"> &#39;(?:\\.|[^&#39;\\])*&#39; # String literal</span> </span><span id="L-9"><a name="L-9"></a><span class="s2"> |</span> </span><span id="L-10"><a name="L-10"></a><span class="s2"> (?:[^/\n&quot;&#39;]|/[^/*\n&quot;&#39;])+ # Any code besides newlines or string literals (essentially no comments)</span> </span><span id="L-11"><a name="L-11"></a><span class="s2"> |</span> </span><span id="L-12"><a name="L-12"></a><span class="s2"> \n # Newline</span> </span><span id="L-13"><a name="L-13"></a><span class="s2"> )+ # Repeat</span> </span><span id="L-14"><a name="L-14"></a><span class="s2"> )|</span> </span><span id="L-15"><a name="L-15"></a><span class="s2"> (/\* (?:[^*]|\*[^/])* \*/) # Multi-line comment</span> </span><span id="L-16"><a name="L-16"></a><span class="s2"> |</span> </span><span id="L-17"><a name="L-17"></a><span class="s2"> (?://(.*)$) # Comment</span> </span><span id="L-18"><a name="L-18"></a><span class="s2">&quot;&quot;&quot;</span> </span><span id="L-19"><a name="L-19"></a><span class="n">re_js_comments</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">re_js_comments_str</span><span class="p">,</span> <span class="n">re</span><span class="o">.</span><span class="n">VERBOSE</span> <span class="o">+</span> <span class="n">re</span><span class="o">.</span><span class="n">MULTILINE</span><span class="p">)</span> </span><span id="L-20"><a name="L-20"></a> </span><span id="L-21"><a name="L-21"></a> </span><span id="L-22"><a name="L-22"></a><span class="k">def</span> <span class="nf">strip_js_comments</span><span class="p">(</span><span class="n">string</span><span class="p">):</span> </span><span id="L-23"><a name="L-23"></a> <span class="sd">&quot;&quot;&quot;Originally obtained from Stackoverflow this function strips JavaScript</span> </span><span id="L-24"><a name="L-24"></a><span class="sd"> (and JSON) comments from a string while considering those encapsulated by strings.</span> </span><span id="L-25"><a name="L-25"></a> </span><span id="L-26"><a name="L-26"></a><span class="sd"> Source: http://stackoverflow.com/questions/2136363/matching-one-line-javascript-comments-with-re</span> </span><span id="L-27"><a name="L-27"></a><span class="sd"> &quot;&quot;&quot;</span> </span><span id="L-28"><a name="L-28"></a> <span class="n">parts</span> <span class="o">=</span> <span class="n">re_js_comments</span><span class="o">.</span><span class="n">findall</span><span class="p">(</span><span class="n">string</span><span class="p">)</span> </span><span id="L-29"><a name="L-29"></a> <span class="c1"># Stripping the whitespaces is, of course, optional, but the columns are fucked up anyway</span> </span><span id="L-30"><a name="L-30"></a> <span class="c1"># with the comments being removed and it doesn&#39;t break things.</span> </span><span id="L-31"><a name="L-31"></a> <span class="k">return</span> <span class="s1">&#39;&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">strip</span><span class="p">(</span><span class="s1">&#39; &#39;</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">parts</span><span class="p">])</span> </span></pre></div> </td></tr></table>
function, python