MAINT bump version to 3.1.0.dev3

README.rst

@@ -158,6 +158,12 @@ This data has a CC BY 4.0 license.
 Please see ``pycantonese/data/rime_cantonese/README.md``
 in the GitHub source code for details.
 
+Logo
+----
+
+The PyCantonese logo is the Chinese character 粵 meaning Cantonese,
+with artistic design by albino.snowman (Instagram handle).
+
 Acknowledgments
 ---------------
 
@@ -176,8 +182,6 @@ Individuals who have contributed feedback, bug reports, etc.
 - Stephan Stiller
 - Tsz-Him Tsui
 
-Logo design by albino.snowman (Instagram handle).
-
 .. end-sphinx-website-index-page
 
 Changelog

docs/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 1404fff678449e59d26f85b0dd69ab69
+config: a156ebd82ec8de5236ada8407d7dc7f0
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/_modules/index.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>Overview: module code &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>Overview: module code &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -291,7 +291,7 @@ <h1>All modules for which code is available</h1>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/corpus.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.corpus &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.corpus &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -651,7 +651,7 @@ <h1>Source code for pycantonese.corpus</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/jyutping/characters.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.jyutping.characters &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.jyutping.characters &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -312,21 +312,31 @@ <h1>Source code for pycantonese.jyutping.characters</h1><div class="highlight"><
         <span class="n">characters_to_jyutping</span><span class="p">[</span><span class="n">character</span><span class="p">]</span> <span class="o">=</span> <span class="n">jp</span>
 
     <span class="n">words_to_jyutping</span> <span class="o">=</span> <span class="p">{</span>
-        <span class="o">**</span><span class="n">words_to_jyutping</span><span class="p">,</span>
-        <span class="o">**</span><span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">CHARS_TO_JYUTPING</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">k</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">},</span>
+        <span class="c1"># The ordering of the following dicts matters. The rime-cantonese</span>
+        <span class="c1"># data may contain what&#39;s been re-segmented by this repo, and may</span>
+        <span class="c1"># contain jyutping pronunciations for particular characters that</span>
+        <span class="c1"># are only used in those contexts. The data from HKCanCor should comes</span>
+        <span class="c1"># last to act as the default to override such cases.</span>
         <span class="o">**</span><span class="p">{</span>
             <span class="n">k</span><span class="p">:</span> <span class="n">v</span>
             <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">LETTERED</span><span class="o">.</span><span class="n">items</span><span class="p">()</span>
             <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">split_characters_with_alphanum</span><span class="p">(</span><span class="n">k</span><span class="p">))</span> <span class="o">&gt;</span> <span class="mi">1</span>
         <span class="p">},</span>
+        <span class="o">**</span><span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">CHARS_TO_JYUTPING</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">k</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">},</span>
+        <span class="o">**</span><span class="n">words_to_jyutping</span><span class="p">,</span>
     <span class="p">}</span>
 
     <span class="c1"># TODO: Extract characters from CHARS_TO_JYUTPING and LETTERED</span>
     <span class="c1">#    and add them to characters_to_jyutping</span>
     <span class="n">characters_to_jyutping</span> <span class="o">=</span> <span class="p">{</span>
-        <span class="o">**</span><span class="n">characters_to_jyutping</span><span class="p">,</span>
-        <span class="o">**</span><span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">CHARS_TO_JYUTPING</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">k</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">},</span>
+        <span class="c1"># The ordering of the following dicts matters. The rime-cantonese</span>
+        <span class="c1"># data may contain what&#39;s been re-segmented by this repo, and may</span>
+        <span class="c1"># contain jyutping pronunciations for particular characters that</span>
+        <span class="c1"># are only used in those contexts. The data from HKCanCor should comes</span>
+        <span class="c1"># last to act as the default to override such cases.</span>
         <span class="o">**</span><span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">LETTERED</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">k</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">},</span>
+        <span class="o">**</span><span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">CHARS_TO_JYUTPING</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">k</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">},</span>
+        <span class="o">**</span><span class="n">characters_to_jyutping</span><span class="p">,</span>
     <span class="p">}</span>
 
     <span class="k">return</span> <span class="n">words_to_jyutping</span><span class="p">,</span> <span class="n">characters_to_jyutping</span>
@@ -405,7 +415,7 @@ <h1>Source code for pycantonese.jyutping.characters</h1><div class="highlight"><
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/jyutping/parse_jyutping.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.jyutping.parse_jyutping &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.jyutping.parse_jyutping &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -431,7 +431,7 @@ <h1>Source code for pycantonese.jyutping.parse_jyutping</h1><div class="highligh
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/jyutping/tipa.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.jyutping.tipa &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.jyutping.tipa &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -424,7 +424,7 @@ <h1>Source code for pycantonese.jyutping.tipa</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/jyutping/yale.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.jyutping.yale &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.jyutping.yale &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -555,7 +555,7 @@ <h1>Source code for pycantonese.jyutping.yale</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/pos_tagging/hkcancor_to_ud.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.pos_tagging.hkcancor_to_ud &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.pos_tagging.hkcancor_to_ud &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -460,7 +460,7 @@ <h1>Source code for pycantonese.pos_tagging.hkcancor_to_ud</h1><div class="highl
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/pos_tagging/tagger.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.pos_tagging.tagger &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.pos_tagging.tagger &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -652,7 +652,7 @@ <h1>Source code for pycantonese.pos_tagging.tagger</h1><div class="highlight"><p
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/stop_words.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.stop_words &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.stop_words &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -439,7 +439,7 @@ <h1>Source code for pycantonese.stop_words</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pycantonese/word_segmentation.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pycantonese.word_segmentation &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pycantonese.word_segmentation &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -278,7 +278,6 @@ <h1>Source code for pycantonese.word_segmentation</h1><div class="highlight"><pr
 <span class="kn">from</span> <span class="nn">pycantonese.data.rime_cantonese</span> <span class="kn">import</span> <span class="p">(</span>
     <span class="n">CHARS_TO_JYUTPING</span><span class="p">,</span>
     <span class="n">LETTERED</span><span class="p">,</span>
-    <span class="n">MAPS</span><span class="p">,</span>
 <span class="p">)</span>
 <span class="kn">from</span> <span class="nn">pycantonese.util</span> <span class="kn">import</span> <span class="n">split_characters_with_alphanum</span>
 
@@ -321,7 +320,6 @@ <h1>Source code for pycantonese.word_segmentation</h1><div class="highlight"><pr
         <span class="c1"># Train with rime-cantonese data.</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">_words</span> <span class="o">|=</span> <span class="n">CHARS_TO_JYUTPING</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">_words</span> <span class="o">|=</span> <span class="n">LETTERED</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">_words</span> <span class="o">|=</span> <span class="nb">set</span><span class="p">(</span><span class="n">MAPS</span><span class="p">)</span>
 
         <span class="c1"># Adjust with the allowed and disallowed words.</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">_words</span> <span class="o">|=</span> <span class="n">allow</span> <span class="ow">or</span> <span class="nb">set</span><span class="p">()</span>
@@ -374,7 +372,7 @@ <h1>Source code for pycantonese.word_segmentation</h1><div class="highlight"><pr
 <span class="sd">    Examples</span>
 <span class="sd">    --------</span>
 <span class="sd">    &gt;&gt;&gt; segment(&quot;廣東話容唔容易學？&quot;)  # &quot;Is Cantonese easy to learn?&quot;</span>
-<span class="sd">    [&#39;廣東話&#39;, &#39;容&#39;, &#39;唔容易&#39;, &#39;學&#39;, &#39;？&#39;]</span>
+<span class="sd">    [&#39;廣東話&#39;, &#39;容&#39;, &#39;唔&#39;, &#39;容易&#39;, &#39;學&#39;, &#39;？&#39;]</span>
 <span class="sd">    &gt;&gt;&gt;</span>
 <span class="sd">    &gt;&gt;&gt; # Customizing the segmentation behavior.</span>
 <span class="sd">    &gt;&gt;&gt; from pycantonese.word_segmentation import Segmenter</span>
@@ -403,7 +401,7 @@ <h1>Source code for pycantonese.word_segmentation</h1><div class="highlight"><pr
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>

docs/_modules/pylangacq/chat.html

@@ -7,7 +7,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>pylangacq.chat &mdash; PyCantonese 3.1.0.dev2 documentation</title>
+  <title>pylangacq.chat &mdash; PyCantonese 3.1.0.dev3 documentation</title>
 
 
 
@@ -66,7 +66,7 @@
 
 
               <div class="version">
-                3.1.0.dev2
+                3.1.0.dev3
               </div>
 
 
@@ -2270,7 +2270,7 @@ <h1>Source code for pylangacq.chat</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on November 26, 2020
+        &copy; Copyright 2014-2020, Jackson L. Lee | Documentation last updated on December 05, 2020
 
     </p>
   </div>