def handle_hskchars():
init_resources()
extralink = ""
expand = get_parameter("expand")
return hsk_vocabulary_page("/hskchars", "HSK Characters for 2012-2020",
extralink, "characters", "/hskwords", "words",
hsk_chars, frequency_order_char_link, expand)
def handle_cidian():
start_time = time.time()
init_resources()
results = []
query = get_parameter("q")
expand = get_parameter("expand")
return cidian_page(expand, query, results, start_time)
def handle_radicals():
start_time = time.time()
init_resources()
expand = get_parameter("expand")
hsk_level = int(get_parameter(
"hsk", 0)) # 1, 2, .. 6 but can be two levels e.g. 12, 14 etc.
return radicals_page(expand, hsk_level, start_time)
def handle_hskchars2010():
init_resources()
expand = get_parameter("expand")
return hsk_vocabulary_page(
'/hskchars2010', "HSK Characters for 2010 (outdated)",
'<a href="/hskchars">HSK Characters 2012-2020</a>', "characters",
"/hskwords2010", "words", hsk_chars_2010, frequency_order_char_link,
expand)
def handle_homophones():
start_time = time.time()
num_chars = int(get_parameter("chars", "2"))
expand = get_parameter("expand", "no") == "yes"
match_tones = get_parameter("tones", "no") == "yes"
hsk_only = get_parameter("hsk", "no") == "yes"
init_resources()
return homophones_page(expand, hsk_only, match_tones, num_chars, start_time)
def perform_set_operations(hanzi_a, hanzi_b, results, expand):
init_resources()
notes = []
if get_parameter("formatA") == "block":
words_a, chars_a, hsk_word_count, hsk_char_count = parse_block(
hanzi_a, notes, expand, word_char_definition_link)
elif get_parameter("formatA") == "commasep":
words_a, chars_a, hsk_word_count, hsk_char_count = parse_comma_sep(
hanzi_a, notes, True, expand, word_char_definition_link)
else:
words_a, chars_a, hsk_word_count, hsk_char_count = parse_list(
hanzi_a, notes, True, expand, word_char_definition_link)
if len(notes):
results.append(
"""<h2><span style="color:red;">Warnings (List A)</span> <a class="arrowlink" href="javascript:toggle_visibility('warningshelp');"><small><small>(?)</small></small></a></h2><ul>
<div id="warningshelp" class="inlinehelp" style="max-width:600px;">
<p>This section lists words and character that are being treated as Chinese but aren't in the CC-CEDICT that is being used.</p>
<p>In addition, when potential word matches are ignored during parsing of a block of text, warnings below will show you
the words that are in the dictionary but which were not chosen by the script.</p>
</div><span style="color:red;">""")
for note in notes:
results.append("<li>{}</li>".format(note))
results.append("</ul></span>")
notes = []
if get_parameter("formatB") == "block":
words_b, chars_b, hsk_word_count, hsk_char_count = parse_block(
hanzi_b, notes, expand, word_char_definition_link)
elif get_parameter("formatB") == "commasep":
words_b, chars_b, hsk_word_count, hsk_char_count = parse_comma_sep(
hanzi_b, notes, True, expand, word_char_definition_link)
else:
words_b, chars_b, hsk_word_count, hsk_char_count = parse_list(
hanzi_b, notes, True, expand, word_char_definition_link)
if len(notes):
results.append(
"""<h2><span style="color:red;">Warnings (List B)</span> <a class="arrowlink" href="javascript:toggle_visibility('warningshelp');"><small><small>(?)</small></small></a></h2><ul>
<div id="warningshelp" class="inlinehelp" style="max-width:600px;">
<p>This section lists words and character that are being treated as Chinese but aren't in the CC-CEDICT that is being used.</p>
<p>In addition, when potential word matches are ignored during parsing of a block of text, warnings below will show you
the words that are in the dictionary but which were not chosen by the script.</p>
</div><span style="color:red;">""")
for note in notes:
results.append("<li>{}</li>".format(note))
results.append("</ul></span>")
joinchar = ""
if get_parameter("outputformat") == "oneperline":
joinchar = "\n"
elif get_parameter("outputformat") == "commasep":
joinchar = ","
elif get_parameter("outputformat") == "tabsep":
joinchar = "\t"
else:
joinchar = " "
results.append(
"""<h4>Set Operations on Words <a class="arrowlink" href="javascript:toggle_visibility('wordoperationshelp');"><small><small>(?)</small></small></a></h4>
<div id="wordoperationshelp" class="inlinehelp" style="max-width:600px;">
<p><b>A<sub>w</sub></b> and <b>B<sub>w</sub></b> are the sets of all unique words derived from Word Lists A and B above.</p>
<p><b>A<sub>w</sub> \u2229 B<sub>w</sub></b> <i>Intersection, words that appear in both sets.</i><br />
<b>A<sub>w</sub> \u222A B<sub>w</sub></b> <i>Union, both sets of words combined together as a single set.</i><br />
<b>A<sub>w</sub> \u2216 B<sub>w</sub></b> <i>Difference, words that are <b>A<sub>w</sub></b> but not <b>B<sub>w</sub></b>.</i><br />
<b>B<sub>w</sub> \u2216 A<sub>w</sub></b> <i>Difference, words that are <b>B<sub>w</sub></b> but not <b>A<sub>w</sub></b>.</i><br />
<b>A<sub>w</sub> \u2206 B<sub>w</sub></b> <i>Symmetric Difference, words that are in only one of the two sets.</i></p>
<p>All sets are sorted with the most frequently used words first.</p>
</div>""")
results.append(
setresultbox("A<sub>w</sub>", "Awords", frequency_order_word(words_a),
joinchar, "word"))
results.append(
setresultbox("B<sub>w</sub>", "Bwords", frequency_order_word(words_b),
joinchar, "word"))
results.append(
setresultbox("A<sub>w</sub> \u2229 B<sub>w</sub>", "AintersectBwords",
frequency_order_word(words_a & words_b), joinchar,
"word"))
results.append(
setresultbox("A<sub>w</sub> \u222A B<sub>w</sub>", "AunionBwords",
frequency_order_word(words_a | words_b), joinchar,
"word"))
results.append(
setresultbox("A<sub>w</sub> \u2216 B<sub>w</sub>", "AdifferenceBwords",
frequency_order_word(words_a - words_b), joinchar,
"word"))
results.append(
setresultbox("B<sub>w</sub> \u2216 A<sub>w</sub>", "BdifferenceAwords",
frequency_order_word(words_b - words_a), joinchar,
"word"))
results.append(
setresultbox("A<sub>w</sub> \u2206 B<sub>w</sub>", "AsymmmetricBwords",
frequency_order_word(words_a ^ words_b), joinchar,
"word"))
results.append(
"""<h4>Set Operations on Characters <a class="arrowlink" href="javascript:toggle_visibility('charoperationshelp');"><small><small>(?)</small></small></a></h4>
<div id="charoperationshelp" class="inlinehelp" style="max-width:600px;">
<p><b>A<sub>c</sub></b> and <b>B<sub>c</sub></b> are the sets of all unique characters derived from Word Lists A and B above.</p>
<p><b>A<sub>c</sub> \u2229 B<sub>c</sub></b> <i>Intersection, characters that appear in both sets.</i><br />
<b>A<sub>c</sub> \u222A B<sub>c</sub></b> <i>Union, both sets of characters combined together as a single set.</i><br />
<b>A<sub>c</sub> \u2216 B<sub>c</sub></b> <i>Difference, characters that are <b>A<sub>c</sub></b> but not <b>B<sub>c</sub></b>.</i><br />
<b>B<sub>c</sub> \u2216 A<sub>c</sub></b> <i>Difference, characters that are <b>B<sub>c</sub></b> but not <b>A<sub>c</sub></b>.</i><br />
<b>A<sub>c</sub> \u2206 B<sub>c</sub></b> <i>Symmetric Difference, characters that are in only one of the two sets.</i></p>
<p>All sets are sorted with the most frequently used characters first.</p>
</div>""")
results.append(
setresultbox("A<sub>c</sub>", "Achars", frequency_order_word(chars_a),
joinchar, "char"))
results.append(
setresultbox("B<sub>c</sub>", "Bchars", frequency_order_word(chars_b),
joinchar, "char"))
results.append(
setresultbox("A<sub>c</sub> \u2229 B<sub>c</sub>", "AintersectBchars",
frequency_order_char(chars_a & chars_b), joinchar,
"char"))
results.append(
setresultbox("A<sub>c</sub> \u222A B<sub>c</sub>", "AunionBchars",
frequency_order_char(chars_a | chars_b), joinchar,
"char"))
results.append(
setresultbox("A<sub>c</sub> \u2216 B<sub>c</sub>", "AdifferenceBchars",
frequency_order_char(chars_a - chars_b), joinchar,
"char"))
results.append(
setresultbox("B<sub>c</sub> \u2216 A<sub>c</sub>", "BdifferenceAchars",
frequency_order_char(chars_b - chars_a), joinchar,
"char"))
results.append(
setresultbox("A<sub>c</sub> \u2206 B<sub>c</sub>", "AsymmmetricBchars",
frequency_order_char(chars_a ^ chars_b), joinchar,
"char"))
def vocab_diff_page(oldlink, newlink, thislink, thisitem, otherlink, otheritem,
oldvocab, newvocab, linkfunction):
start_time = time.time()
init_resources()
expand = get_parameter("expand")
results = []
results.append("""<html lang="zh-Hans">\n<head>""")
results.append(
"<title>HSK\u4E1C\u897F - Where the HSK 2010 {} are in 2012-2020</title>"
.format(thisitem[0].upper() + thisitem[1:]))
results.append(allstyle)
results.append("</head>\n<body>")
results.append(
"""<a href="https://hskhsk.com/word-lists">HSK\u4E1C\u897F</a>""")
results.append("""<a href="/">Scripts</a>""")
results.append(
"""<a href="{}">Where the HSK 2010 {} are in 2012-2020</a>""".format(
otherlink, otheritem[0].upper() + otheritem[1:]))
results.append(
"<h3>HSK 2010 {} that changed level in 2012-2020</h3>".format(
thisitem[0].upper() + thisitem[1:]))
results.append(
"""<p>This table shows the {0} in the New HSK 2010 that changed level when the word lists were revised
in 2012 (also valid to date as of 2020), {0} that didn't change level are shown below.
For definitions hover over the characters, or try clicking on almost anything.</p>
<table border="1" style="border-collapse:collapse;" cellpadding="2em" cellspacing="0">
<tr><th rowspan=2 colspan=2 style="background-color: #FFFFFF;"></th><th colspan=7><a href="{1}" class="hsk0">HSK 2012-2020</a></th></tr>
<tr>""".format(thisitem, newlink))
for i in range(1, 7):
results.append(
"""<th><div style="white-space: nowrap;"> <a href="{}#hsk{}" class="hsk{}">HSK {}</a> </div></th>"""
.format(newlink, i, i, i))
results.append(
"""<th><div class="hsk0" style="white-space: nowrap;"> Non-HSK </div></th></tr>"""
)
for old in range(1, 8):
results.append("<tr>")
if old == 1:
results.append(
"""<th rowspan=7><a href="{}" class="hsk0">HSK 2010</a></th>"""
.format(oldlink))
if old == 7:
results.append(
"""<th><div style="white-space: nowrap;">Non-HSK</div></th>""")
else:
results.append(
"""<th><div style="white-space: nowrap;"><a href="{}#hsk{}" class="hsk{}">HSK {}</a></div></th>"""
.format(oldlink, old, old, old))
for new in range(1, 8):
if old == new:
if old >= 1 and old <= 6:
results.append(
"""<td class="hsk{0}light" onClick="document.location.href='#hsk{0}';" onmouseover="this.style.cursor='pointer';"> </td>"""
.format(old))
else:
results.append("""<td class="hsk0light"></td>""")
else:
if old == 7:
somehanzi = newvocab[new] - oldvocab[16]
elif new == 7:
somehanzi = oldvocab[old] - newvocab[16]
else:
somehanzi = (oldvocab[old] & newvocab[new]) - newvocab[
old] # add the set subtract to account for case where word exists at multiple levels
results.append("<td>")
separator = "<br />" if expand == "yes" else chinese_comma_sep
results.append(separator.join(linkfunction(somehanzi, expand)))
results.append("</td>")
results.append("</tr>")
results.append("</table>")
results.append(
"<h3>HSK 2010 {} that didn't change level in 2012-2020</h3>".format(
thisitem[0].upper() + thisitem[1:]))
for level in range(1, 7):
results.append(
"""<h4><a class="hsk{0}" name="hsk{0}">HSK {0} {1} that didn't change level</a></h4>"""
.format(level, thisitem[0].upper() + thisitem[1:]))
somehanzi = newvocab[level] & oldvocab[level]
separator = "<br />" if expand == "yes" else chinese_comma_sep
results.append(separator.join(linkfunction(somehanzi, expand)))
results.append(
"""<p><small><i>Page generated in {:1.6f} seconds.</i></small></p>\n"""
.format(time.time() - start_time))
results.append(page_footer)
return Response(results)
def performactions(hanzi, results, expand):
init_resources()
# only parse if one of these actions is being performed
if (get_parameter("analysevocab") or get_parameter("analysehskwords")
or get_parameter("analysehskchars")
or get_parameter("suggesthskwords")
or get_parameter("suggesthskchars")
or get_parameter("suggestwords")
or get_parameter("suggestwordsreuse")
or get_parameter("suggestchars")):
notes = []
if get_parameter("format") == "block":
words, chars, hsk_word_count, hsk_char_count = parse_block(
hanzi, notes, expand)
elif get_parameter("format") == "commasep":
words, chars, hsk_word_count, hsk_char_count = parse_comma_sep(
hanzi, notes, False, expand)
else:
words, chars, hsk_word_count, hsk_char_count = parse_list(
hanzi, notes, False, expand)
if len(notes):
results.append(
"""<h2><span style="color:red;">Warnings</span> <a class="arrowlink" href="javascript:toggle_visibility('warningshelp');"><small><small>(?)</small></small></a></h4><ul>
<div id="warningshelp" class="inlinehelp" style="max-width:500px;">
<p>This section lists words and character that are being treated as Chinese but aren't in the CC-CEDICT that is being used.</p>
<p>In addition, when potential word matches are ignored during parsing of a block of text, warnings below will show you
the words that are in the dictionary but which were not chosen by the script.</p>
</div><span style="color:red;">""")
for note in notes:
results.append("<li>{}</li>".format(note))
results.append("</ul></span>")
results.append(
"""<h2>Results <a class="arrowlink" href="javascript:toggle_visibility('resultshelp');"><small><small>(?)</small></small></a></h4>
<div id="resultshelp" class="inlinehelp" style="max-width:500px;">
All word/character lists are in descending order of frequency, with the most frequently used words/characters at the top of each list.
</div>""")
if get_parameter("analysevocab"):
analysewords(results, words, chars, hsk_word_count, hsk_char_count)
if get_parameter("analysehskwords"):
analysehskwords(results, words, hsk_word_count)
if get_parameter("analysehskchars"):
analysehskchars(results, chars, hsk_char_count)
if get_parameter("suggesthskwords"):
suggesthskwords(results, words)
if get_parameter("suggesthskchars"):
suggesthskchars(results, chars)
if get_parameter("suggestwords"):
suggestfreqwords(results, words)
if get_parameter("suggestwordsreuse"):
suggestfreqwordsre(results, words, chars)
if get_parameter("suggestchars"):
suggestfreqchars(results, chars)
else:
results.append("<h2>Results</h2>")
# these actions just use the raw hanzi
if get_parameter("annotatewords"):
annotatewords(results, hanzi, expand)
if get_parameter("annotatechars"):
annotatechars(results, hanzi, expand)
def handle_mandcomp():
start_time = time.time()
init_resources()
expand = get_parameter("expand")
return mandarin_companion_page(start_time, expand)
def handle_chars1000():
start_time = time.time()
init_resources()
expand = get_parameter("expand")
return list_page_chars1000(expand, start_time)
def handle_flashcards():
init_resources()
return flashcards_download()
def handle_search():
start_time = time.time()
init_resources()
return search_page(start_time)
