Dustin/jp_text_parsing
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sub cues now a bit better at finding words.

Browse Source
This commit is contained in:
Nitsud Yarg 2026-06-26 17:22:48 -07:00
parent e888384af1
commit 4fddddedd2
2 changed files with 42 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
fugashi_parser.py
View File

@ -141,7 +141,7 @@ def get_card_proficiency(query="deck:current"):
elif queue_state == 3:
status = "Relearning"
color = 'lime'
elif queue_state == 2:
elif queue_state == 2 or queue_state == -2:
# Review card split by 21-day threshold
if interval >= 21:
status = "Mature"
@ -149,11 +149,11 @@ def get_card_proficiency(query="deck:current"):
else:
status = "Young"
color = 'cyan'
elif queue_state < 0:
elif queue_state == -1:
status = "Suspended"
color = ''
else:
status = f"Unknown (Queue {queue})"
status = f"Unknown (Queue {queue_state})"
color = ''
word = ''
@ -166,8 +166,10 @@ def get_card_proficiency(query="deck:current"):
if (card_proficiency.get(word)):
print("Multiple matches for word")
if (card_proficiency[word]['State'] < queue_state):
card_proficiency[word] = {'Status' : status,'State' : queue_state, 'Color' : color}
else:
card_proficiency[word] = {'Status' : status,'State' : status, 'Color' : color}
card_proficiency[word] = {'Status' : status,'State' : queue_state, 'Color' : color }
print(f"Card ID {card_id} (State: {queue_state}):")
print(f" Reps: {reps} | Lapses: {lapses} | Interval: {interval} days | Ease: {status} \n")
@ -176,7 +178,13 @@ def get_card_proficiency(query="deck:current"):
# Example usage: Evaluate proficiency for all cards in a specific deck
# get_card_proficiency(query='deck:"Your Deck Name Here"')
try:
proficiency_stats = get_card_proficiency(query='deck:"Japanese Vocab" card:0')
with open('vocab-cache.json', "w", encoding="utf-8") as f:
json.dump(proficiency_stats, f, ensure_ascii=False, indent=2)
except:
with open("vocab-cache.json", "r", encoding="utf-8") as f:
proficiency_stats = json.load(f)
CONTENT_LINK_TAG = {
'名詞': 'meishi', # noun
@ -216,30 +224,38 @@ def should_ruby(surface, reading_hiragana):
return True
def build_ruby(surface: str, reading: str) -> str:
if not reading or not has_japanese(surface):
return html.escape(surface)
def build_ruby(token :TokenReading) -> str:
if not token.reading_hiragana or not has_japanese(token.surface):
return html.escape(token.surface)
style_attr = ''
if proficiency_stats.get(surface):
if proficiency_stats[surface]['Color'] != '':
style_attr = f"style=\"color:{proficiency_stats[surface]['Color']}\""
if surface == reading:
return f"<span {style_attr}>{html.escape(surface)}</span>"
return f"<ruby {style_attr}>{html.escape(surface)}<rt>{html.escape(reading)}</rt></ruby>"
# First try lemma then try surface
if proficiency_stats.get(token.lemma):
if proficiency_stats[token.lemma]['Color'] != '':
style_attr = f"style=\"color:{proficiency_stats[token.lemma]['Color']}\""
elif proficiency_stats.get(token.surface):
if proficiency_stats[token.surface]['Color'] != '':
style_attr = f"style=\"color:{proficiency_stats[token.surface]['Color']}\""
if token.surface == token.reading_hiragana:
return f"<span {style_attr}>{html.escape(token.surface)}</span>"
return f"<ruby {style_attr}>{html.escape(token.surface)}<rt>{html.escape(token.reading_hiragana)}</rt></ruby>"
def build_sub_cue(surface: str, reading: str) -> str:
if not reading or not has_japanese(surface):
return html.escape(surface)
def build_sub_cue(token :TokenReading) -> str:
if not token.reading_hiragana or not has_japanese(token.surface):
return html.escape(token.surface)
# Check if color
color_prefix = ''
color_suffix = ''
if proficiency_stats.get(surface):
if proficiency_stats[surface]['Color'] != '':
color_prefix = f"<c.{proficiency_stats[surface]['Color']}>"
if proficiency_stats.get(token.lemma):
if proficiency_stats[token.lemma]['Color'] != '':
color_prefix = f"<c.{proficiency_stats[token.lemma]['Color']}>"
color_suffix = f"</c>"
if surface == reading:
return f"{color_prefix}{html.escape(surface)}{color_suffix}"
return f"{color_prefix}<ruby>{html.escape(surface)}<rt>{html.escape(reading)}</rt></ruby>{color_suffix}"
elif proficiency_stats.get(token.surface):
if proficiency_stats[token.surface]['Color'] != '':
color_prefix = f"<c.{proficiency_stats[token.surface]['Color']}>"
color_suffix = f"</c>"
if token.surface == token.reading_hiragana:
return f"{color_prefix}{html.escape(token.surface)}{color_suffix}"
return f"{color_prefix}<ruby>{html.escape(token.surface)}<rt>{html.escape(token.reading_hiragana)}</rt></ruby>{color_suffix}"
def build_kana(surface: str, reading: str) -> str:
if not reading or surface == reading or not has_japanese(surface):
@ -459,8 +475,8 @@ def analyze(text: str, vocab: Dict[str, Dict]):
token = TokenReading(surface, reading, lemma, lemma_reading, pos)
tokens.append(token)
ruby_parts.append(build_ruby(surface, reading))
subtitle_parts.append(build_sub_cue(surface, reading))
ruby_parts.append(build_ruby(token))
subtitle_parts.append(build_sub_cue(token))
kana_parts.append(build_kana(surface, reading))
predicate_chunks = chunk_predicates(tokens)

2
process_markdown.py
View File

@ -45,7 +45,7 @@ def main():
result = analyze(lines[i],vocab)
## If the line changed at all
if lines[i] != result['ruby_html']:
lines[i] = '<span>' + result['ruby_html'] + '</span>' + "\n> [!summary]- Vocab\n>" + result['notes_link'] + "\n\n" # lost the new line
lines[i] = '<span><details><summary>' + result['ruby_html'] + '</summary>' + lines[i] + '</span>' + "\n> [!summary]- Vocab\n>" + result['notes_link'] + "\n\n" # lost the new line
file_changed = True
i+=1