def analysewords(results, words, chars, hsk_word_count, hsk_char_count):
results.append("<h4>Analysis of Words/Characters in Input</h4>")
singlecharcount = len([w for w in words if len(w) == 1])
wordcount = len(words)
charcount = len(chars)
totalwords = sum(hsk_word_count.values())
totalchars = sum(hsk_char_count.values())
subtlexwords = subtlex_word_set & words
ccedictwords = cedict_word_set & words
results.append("""Input contained:<ul>
<li>{} unique single-character entries</li>
<li>{} unique multi-character entries</li>
<li>{} unique entries</li>
<li>{} total entries</li>
<li>{} unique characters</li>
<li>{} total characters</li>
<li>{} unique words as recognised by SUBTLEX-CH</li>
<li>{} unique words as recognised by CC-CEDICT</li>
</ul>""".format(singlecharcount, wordcount - singlecharcount, wordcount,
totalwords, charcount, totalchars, len(subtlexwords),
len(ccedictwords)))
wordsknown = "\n".join(frequency_order_word(words))
charsknown = "\n".join(frequency_order_char(chars))
subtlexknown = "\n".join(frequency_order_word(subtlexwords))
ccedictknown = "\n".join(frequency_order_word(ccedictwords))
results.append(blockboxtemplate().format("Unique Entries", "wordsknown",
wordsknown))
results.append(blockboxtemplate().format("Unique Characters", "charsknown",
charsknown))
results.append(blockboxtemplate().format("SUBTLEX Words", "subtlexknown",
subtlexknown))
results.append(blockboxtemplate().format("CC-CEDICT Words", "cedictknown",
ccedictknown))
def suggesthskchars(results, chars):
results.append("""<h4>Suggested HSK Characters not in Input</h4>""")
for i in range(1, 7):
charstolearn = "\n".join(frequency_order_char(hsk_chars[i] - chars))
results.append(blockboxtemplate().format("HSK " + str(i),
"hskcharstolearn" + str(i),
charstolearn))
foundchars = []
for freq, char in char_frequency_ordered:
if char not in chars and char not in hsk_chars[16]:
foundchars.append(char)
if len(foundchars) >= 1000:
break
charstext = "\n".join(frequency_order_char(foundchars))
results.append(blockboxtemplate().format("Non-HSK",
"nonhskcharstolearn" + str(i),
charstext))
def suggesthskwords(results, words):
results.append("""<h4>Suggested HSK Words not in Input</h4>""")
for i in range(1, 7):
wordstolearn = "\n".join(frequency_order_word(hsk_words[i] - words))
results.append(blockboxtemplate().format("HSK " + str(i),
"hskwordstolearn" + str(i),
wordstolearn))
foundwords = []
for freq, word in word_frequency_ordered:
if word not in words and word not in hsk_words[16]:
foundwords.append(word)
if len(foundwords) >= 1000:
break
wordstext = "\n".join(frequency_order_word(foundwords))
results.append(blockboxtemplate().format("Non-HSK",
"nonhskwordstolearn" + str(i),
wordstext))
def setresultbox(title, idname, itemset, joinchar, itemname):
setlen = len(itemset)
if setlen == 0:
titlewithsize = title + """<span style="font-weight: lighter; font-size: 80%; font-style: italic;"> (empty)</span>"""
else:
titlewithsize = title + """<span style="font-weight: lighter; font-size: 80%; font-style: italic;"> ({} {}{})</span>""".format(
setlen, itemname, "s" if setlen > 1 else "")
return blockboxtemplate().format(titlewithsize, idname,
joinchar.join(itemset))
def analysehskchars(results, chars, hsk_char_count):
knownintersect = {}
results.append("<h4>Analysis of HSK Characters in Input</h4>")
results.append("Input contained:<ul>")
cumulativeknown = {}
cumulativetotal = {}
cumulativeknown[0] = 0
cumulativetotal[0] = 0
numknown = {}
numhsk = {}
for i in range(1, 7):
knownintersect[i] = chars & hsk_chars[i]
numknown[i] = len(knownintersect[i])
numhsk[i] = len(hsk_chars[i])
percentknown = 100 * float(numknown[i]) / numhsk[i]
cumulativeknown[i] = cumulativeknown[i - 1] + numknown[i]
cumulativetotal[i] = cumulativetotal[i - 1] + numhsk[i]
results.append(
"""<li>{} ({:.2f}%) of the {} HSK {} characters""".format(
numknown[i], percentknown, numhsk[i], i))
if i > 1 > 0:
cumpercentknown = 100 * float(
cumulativeknown[i]) / cumulativetotal[i]
results.append(
""" <i>(Cumulative: {} ({:.2f}%) of the {} HSK 1-{} characters)</i>"""
.format(cumulativeknown[i], cumpercentknown,
cumulativetotal[i], i))
results.append("</li>")
results.append("</ul>")
totalunique = len(chars)
if totalunique > 0:
numknown_nonhsk = totalunique - cumulativeknown[6]
results.append(
"Of the {} <b>unique</b> characters in the input:<ul>".format(
totalunique))
for i in range(1, 7):
percentknown = 100 * float(numknown[i]) / totalunique
results.append(
"""<li>{} ({:.2f}%) were HSK {} characters""".format(
numknown[i], percentknown, i))
if i > 1:
cumpercentknown = 100 * float(cumulativeknown[i]) / totalunique
results.append(
"""<i>(Cumulative: {} ({:.2f}%) were HSK 1-{} characters)</i>"""
.format(cumulativeknown[i], cumpercentknown, i))
results.append("</li>")
numknown_nonhsk_percent = 100 * float(numknown_nonhsk) / totalunique
results.append(
"""<li>{} ({:.2f}%) were non-HSK characters</li>""".format(
numknown_nonhsk, numknown_nonhsk_percent))
results.append("</ul>")
totalchars = sum(hsk_char_count.values())
if totalchars == totalunique:
results.append(
"<p><i>Each character appeared only once in the input.</i></p>")
else:
cumknown = 0
results.append(
"Of the {} <b>total</b> characters that were input:<ul>".format(
totalchars))
for i in range(1, 7):
percentknown = 100 * float(hsk_char_count[i]) / totalchars
cumknown += hsk_char_count[i]
results.append(
"""<li>{} ({:.2f}%) were HSK {} characters""".format(
hsk_char_count[i], percentknown, i))
if i > 1:
cumpercentknown = 100 * float(cumknown) / totalchars
results.append(
"""<i>(Cumulative: {} ({:.2f}%) were HSK 1-{} characters)</i>"""
.format(cumknown, cumpercentknown, i))
results.append("</li>")
num_nonhsk = totalchars - cumknown
numknown_nonhsk_percent = 100 * float(num_nonhsk) / totalchars
results.append(
"""<li>{} ({:.2f}%) were non-HSK characters</li>""".format(
num_nonhsk, numknown_nonhsk_percent))
results.append("</ul>")
for i in range(1, 7):
charsknown = "\n".join(frequency_order_char(knownintersect[i]))
results.append(blockboxtemplate().format("HSK " + str(i),
"hskcharsknown" + str(i),
charsknown))
nonhskchars = "\n".join(frequency_order_char(chars - hsk_chars[16]))
results.append(blockboxtemplate().format("Non-HSK", "nonhskcharsknown",
nonhskchars))