def parse_block(hanzi, notes, expand, definition_link_function):
hsk_word_count = {0: 0, 1: 0, 2: 0, 3: 0, 4: 0, 5: 0, 6: 0}
hsk_char_count = {0: 0, 1: 0, 2: 0, 3: 0, 4: 0, 5: 0, 6: 0}
words = set()
chars = set()
ignore_chars = set()
unknown_chars = set()
tokenised = mostlikelywordsallchars(hanzi, expand, definition_link_function, notes)
for ishanzi, text in tokenised:
if ishanzi:
for char in text:
chars.add(char)
hsk_char_count[get_hsk_char_level(char)] += 1
if char not in char_freq:
unknown_chars.add(char)
words.add(text)
hsk_word_count[get_hsk_word_level(text)] += 1
else:
ignore_chars.add(text)
if len(ignore_chars):
notes.append(
"Ignored characters: " + ", ".join([definition_link_function(h, "none", expand) for h in ignore_chars]))
if len(unknown_chars):
notes.append(
"Unknown characters: " + ", ".join([definition_link_function(h, "none", expand) for h in unknown_chars]))
return words, chars, hsk_word_count, hsk_char_count
def init_radical_data():
for char, freq in char_freq.items():
if char in cc_radicalof:
radical = cc_radicalof[char]
if radical not in radical_freq:
radical_freq[radical] = 0
radical_freq[radical] += freq
radical_level = get_hsk_char_level(radical)
char_level_char = get_hsk_char_level(char)
if char_level_char != 0 and char_level_char < radical_level:
radical_level = char_level_char
if ((radical in hsk_radical_level
and radical_level < hsk_radical_level[radical]
and radical_level != 0)
or (radical not in hsk_radical_level)):
hsk_radical_level[radical] = radical_level
frequency_order = [(freq, radical)
for (radical, freq) in radical_freq.items()]
frequency_order.sort()
frequency_order.reverse()
for i in range(len(frequency_order)):
radical_frequency_index[frequency_order[i][1]] = i + 1
def parse_list(hanzi, notes, allownonhanzi, expand, definition_link_function):
hsk_word_count = {0: 0, 1: 0, 2: 0, 3: 0, 4: 0, 5: 0, 6: 0}
hsk_char_count = {0: 0, 1: 0, 2: 0, 3: 0, 4: 0, 5: 0, 6: 0}
words = set()
chars = set()
ignore_words = set()
ignore_chars = set()
unknown_words = set()
unknown_chars = set()
for line in hanzi.split("\n"):
chunks = line.split()
if len(chunks):
word = chunks[0]
if allownonhanzi or len([c for c in word if not char_is_ok(c)]) == 0:
words.add(word)
hsk_word_count[get_hsk_word_level(word)] += 1
if (not allownonhanzi) and word not in word_freq:
unknown_words.add(word)
else:
ignore_words.add(word)
for char in word:
if allownonhanzi or char_is_ok(char):
chars.add(char)
hsk_char_count[get_hsk_char_level(char)] += 1
if (not allownonhanzi) and char not in char_freq:
unknown_chars.add(char)
else:
ignore_chars.add(char)
if len(ignore_words):
notes.append(
"Ignored words: " + ", ".join([definition_link_function(h, "none", expand) for h in ignore_words]))
if len(ignore_chars):
notes.append(
"Ignored characters: " + ", ".join([definition_link_function(h, "none", expand) for h in ignore_chars]))
if len(unknown_words):
notes.append(
"Unknown words: " + ", ".join([definition_link_function(h, "none", expand) for h in unknown_words]))
if len(unknown_chars):
notes.append(
"Unknown characters: " + ", ".join([definition_link_function(h, "none", expand) for h in unknown_chars]))
return words, chars, hsk_word_count, hsk_char_count
def hanzi_definition_link(results, hanziword, hanzichar, colour, expand):
r"""
Keyword arguments:
colour -- can be 'char', 'word', 'none', 'auto'
"""
urlstub = "/cidian?{}q=".format("expand=yes&" if expand == "yes" else "")
url = urlstub + urllib.parse.quote(html.escape(hanziword))
title = get_linktext_hanzi_info(hanziword, hanzichar, 30)
wordlevel = get_hsk_word_level(hanziword)
charlevel = get_hsk_char_level(hanzichar)
radicallevel = get_hsk_radical_level(hanzichar)
linkclass = "definition"
if (colour == "word" or colour == "auto") and wordlevel > 0:
linkclass = "hsk{3}"
elif (colour == "char" or colour == "auto") and charlevel > 0:
linkclass = "hsk{4}"
elif colour == "radical":
linkclass = "hsk{5}"
link_format = '<a class="' + linkclass + '" href="{0}" title="{1}">{2}</a>'
results.append(
link_format.format(url, html.escape(title), html.escape(hanzichar),
wordlevel, charlevel, radicallevel))