nevo/hebrew_flash_cards
1
0
Fork 0
Code Issues Pull requests Projects Releases 11 Packages Wiki Activity Actions

feat: confusables show ktiv male, emoji/prep stripping fully upstream

Browse source 
- Confusables deck front now shows shared ktiv male form instead of
  nikkud variants joined by "/". Back still shows nikkud with definitions.
- Fixed list scraper EMOJI_RE to catch variation selectors (U+FE0F) and
  ZWJ (U+200D) — cleaned 17 entries with leftover selectors in meaning.
- Removed build-time prep extraction fallback (0 entries relied on it).
- release.py: fix keeshare field name (API_TOKEN → password).

Closes: Pealim #11 (emoji/prep upstream), Pealim #16 (confusables ktiv male)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Sochen 2026-03-21 02:19:03 +00:00
parent 138acb06d8
commit f3496998f5
4 changed files with 76 additions and 51 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

89
apkg_builder.py
View file

@ -265,6 +265,14 @@ details[open] > .more-header::before { content: "● "; }
text-align: center;
margin: 0.3em 0;
}
.plural-direction {
font-size: 32px;
color: #444;
text-align: center;
direction: rtl;
margin: 8px 0;
font-weight: bold;
}
.card [type="button"], .card button, .replay-button {
display: block !important;
margin: 4px auto !important;
@ -288,7 +296,26 @@ details[open] > .more-header::before { content: "● "; }
.related-header { color: #999; }
.rw-word { color: #e0e0e0; }
.rw-meaning { color: #999; }
.plural-direction { color: #aaa; }
}
.nightMode .card { color: #e8e8e8; background: #1c1c1e; }
.nightMode .hebrew { color: #f0f0f0; }
.nightMode .hebrew-sm { color: #e0e0e0; }
.nightMode .meaning { color: #82b0ff; }
.nightMode .sec-label { color: #e0e0e0; }
.nightMode .sec-key { color: #e0e0e0; }
.nightMode .sec-val { color: #e0e0e0; }
.nightMode .conf-entry { color: #ddd; }
.nightMode .hint { color: #777; }
.nightMode .voice-label { color: #888; }
.nightMode .example { color: #e0e0e0; border-right-color: #555; }
.nightMode .divider { border-top-color: #333; }
.nightMode .freq-badge { color: #888; border-color: #444; }
.nightMode .more-header { color: #bbb; background: #2a2a2e; border-color: #555; }
.nightMode .related-header { color: #999; }
.nightMode .rw-word { color: #e0e0e0; }
.nightMode .rw-meaning { color: #999; }
.nightMode .plural-direction { color: #aaa; }
"""
# ──────────────────────────────────────────────────────────────────────────────
@ -422,7 +449,7 @@ CONJ_BACK = """
<div class="hebrew">{{ConjugatedForm}}{{#Prep}} ({{Prep}}){{/Prep}}</div>
{{#Audio}}<div>{{Audio}}</div>{{/Audio}}
<details class="more-toggle"><summary class="more-header">מידע נוסף</summary>
{{#Meaning}}<div class="sec-label" style="text-align:center;display:block;">{{Meaning}}</div>{{/Meaning}}
{{#Meaning}}<div class="meaning" style="font-size:28px;">{{Meaning}}</div>{{/Meaning}}
<div class="sec-table">
<div class="sec-label"><span class="sec-key">שֹׁרֶשׁ:</span><span class="sec-val">{{Root}}</span></div>
<div class="sec-label"><span class="sec-key">בִּנְיָן:</span><span class="sec-val">{{Binyan}}</span></div>
@ -860,7 +887,6 @@ def build_vocab_deck(
meaning = re.sub(r"\s{2,}", " ", meaning).strip(", ;:")
meaning = re.sub(r"(\w)\(", r"\1 (", meaning) # space before opening paren
meaning = re.sub(r",(\S)", r", \1", meaning) # space after comma
meaning_raw = entry.get("meaning_raw", "") or ""
slug = entry.get("slug", "") or ""
frequency = entry.get("frequency") or 999_999
audio_file = entry.get("audio_file", "") or ""
@ -906,14 +932,9 @@ def build_vocab_deck(
emoji_str = emoji_lookup[kw]
break
# Extract Hebrew prepositions: prefer upstream-parsed prep field, fall back to meaning_raw scan
# (fallback covers entries scraped before prep was moved upstream)
# Hebrew prepositions — extracted upstream by list scraper
entry_prep = entry.get("prep")
if entry_prep:
prep_str = " ".join(f"({p})" for p in entry_prep.split())
else:
preps = HBPAREN_RE.findall(meaning_raw)
prep_str = " ".join(f"({p})" for p in preps)
prep_str = " ".join(f"({p})" for p in entry_prep.split()) if entry_prep else ""
# Audio — use audio_file from entry; for confusables it's already slug-based
audio_tag = ""
@ -1123,25 +1144,12 @@ def build_conj_deck(
root = ".".join(root_list)
voice = VOICE_MAP.get(binyan, "")
meaning_raw = entry.get("meaning_raw", "") or ""
meaning = entry.get("meaning", "") or ""
# Extract Hebrew preposition — strip from meaning, show on Hebrew side
# Hebrew preposition — extracted upstream by scraper
prep_str = ""
conj_prep = conj.get("prep")
conj_prep = conj.get("prep") or entry.get("prep")
if conj_prep:
# Strip any parentheses from stored prep value
prep_str = conj_prep.strip("() ")
elif meaning_raw:
preps = HBPAREN_RE.findall(meaning_raw)
if preps:
prep_str = preps[0]
# Strip Hebrew prepositions from English meaning to avoid duplication
if prep_str:
meaning = HBPAREN_RE.sub("", meaning).strip()
# Also strip from meaning_raw patterns like "(על)"
meaning = re.sub(r"\(\s*" + re.escape(prep_str) + r"\s*-?\s*\)", "", meaning).strip()
# Clean up double spaces and trailing commas
meaning = re.sub(r"\s{2,}", " ", meaning).strip(", ")
related = [(f, w, m) for f, w, m in root_words.get(root, []) if w != infinitive]
if related:
@ -1461,7 +1469,7 @@ def build_confusables_deck(
continue
word_no_nik = unique_entries[0]["word"].get("ktiv_male", "")
words_display = " / ".join(e["word"]["nikkud"] for e in unique_entries)
words_display = word_no_nik # Show ktiv male (shared form) on front
defs_parts: list[str] = []
audio_parts: list[str] = []
@ -1530,8 +1538,8 @@ def write_conf_apkg(
PLURAL_FRONT_SG = """
<div class="hebrew" style="color:#1a1a8c;">{{Singular}}</div>
{{#SingularAudio}}<div>{{SingularAudio}}</div>{{/SingularAudio}}
<div class="sec-label">{{Meaning}}</div>
<div class="hint" style="font-size:28px;">יָחִיד ← רַבִּים</div>
<div class="meaning" style="font-size:28px;">{{Meaning}}</div>
<div class="plural-direction">יָחִיד ← רַבִּים</div>
"""
PLURAL_BACK_SG = """
@ -1547,14 +1555,14 @@ PLURAL_BACK_SG = """
PLURAL_FRONT_PL = """
<div class="hebrew" style="color:#1a1a8c;">{{Plural}}</div>
{{#PluralAudio}}<div>{{PluralAudio}}</div>{{/PluralAudio}}
<div class="hint" style="font-size:28px;">רַבִּים ← יָחִיד</div>
<div class="plural-direction">רַבִּים ← יָחִיד</div>
"""
PLURAL_BACK_PL = """
{{FrontSide}}<hr>
<div class="hebrew">{{Singular}}</div>
{{#SingularAudio}}<div>{{SingularAudio}}</div>{{/SingularAudio}}
<div class="sec-label" style="text-align:center;display:block;">{{Meaning}}</div>
<div class="meaning" style="font-size:28px;">{{Meaning}}</div>
<div class="sec-table">
{{#Gender}}<div class="sec-label"><span class="sec-key">מִין:</span><span class="sec-val">{{Gender}}</span></div>{{/Gender}}
{{#Mishkal}}<div class="sec-label"><span class="sec-key">מִשְׁקָל:</span><span class="sec-val">{{Mishkal}}</span></div>{{/Mishkal}}
@ -1651,9 +1659,9 @@ def build_plural_deck(
irregular_count = len(irregulars)
target_regular = irregular_count * 2
mishkal_count = len(by_mishkal) or 1
per_mishkal = max(2, target_regular // mishkal_count)
# Over-sample per mishkal to compensate for small patterns, then trim
per_mishkal = max(3, (target_regular * 3) // (mishkal_count * 2))
selected: list[tuple[str, dict, dict]] = list(irregulars)
regular_pool: list[tuple[str, dict, dict]] = []
for _mishkal, entries in sorted(by_mishkal.items()):
entries.sort(key=lambda e: e[1].get("frequency") or 999_999)
@ -1664,7 +1672,24 @@ def build_plural_deck(
regular_pool.sort(key=lambda e: e[1].get("frequency") or 999_999)
regular_pool = regular_pool[:target_regular]
selected.extend(regular_pool)
# Sort both pools by frequency, then interleave for homogeneous 2:1 regular:irregular
irregulars.sort(key=lambda e: e[1].get("frequency") or 999_999)
regular_pool.sort(key=lambda e: e[1].get("frequency") or 999_999)
# Interleave: for every 1 irregular, insert 2 regulars
selected: list[tuple[str, dict, dict]] = []
ri = 0 # regular index
for _ii, irr in enumerate(irregulars):
# Insert 2 regulars before each irregular (when available)
for _ in range(2):
if ri < len(regular_pool):
selected.append(regular_pool[ri])
ri += 1
selected.append(irr)
# Append remaining regulars
while ri < len(regular_pool):
selected.append(regular_pool[ri])
ri += 1
note_count = 0
for _unique_key, entry, noun_inflection in selected:

34
data/words.json
View file

@ -28003,7 +28003,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ motorbike, motorcycle",
"meaning": "motorbike, motorcycle",
"meaning_raw": "🏍️ motorbike, motorcycle",
"audio_url": "https://audio.pealim.com/v0/1s/1s8poqw78fk8v.mp3",
"audio_file": "אופנוע.mp3",
@ -107000,7 +107000,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ stadium",
"meaning": "stadium",
"meaning_raw": "🏟️ stadium",
"audio_url": "https://audio.pealim.com/v0/vl/vln4sqr0ez7n.mp3",
"audio_file": "אצטדיון.mp3",
@ -197835,7 +197835,7 @@
],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "recreation, leisure, pleasure️; spending (time, resource)",
"meaning": "recreation, leisure, pleasure; spending (time, resource)",
"meaning_raw": "recreation, leisure, pleasure🏖️; spending (time, resource)",
"audio_url": "https://audio.pealim.com/v0/12/12s7w66rute00.mp3",
"audio_file": "בילוי.mp3",
@ -573280,7 +573280,7 @@
],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ smile",
"meaning": "smile",
"meaning_raw": "☺️ smile",
"audio_url": "https://audio.pealim.com/v0/1o/1o0qkdlzzgz5y.mp3",
"audio_file": "חיוך.mp3",
@ -723335,7 +723335,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ telephone; (coll.) telephone call",
"meaning": "telephone; (coll.) telephone call",
"meaning_raw": "☎️ telephone; (coll.) telephone call",
"audio_url": "https://audio.pealim.com/v0/q4/q4vlmpn3xv25.mp3",
"audio_file": "טלפון.mp3",
@ -768548,7 +768548,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "diamond; ️ diamonds (cards)",
"meaning": "diamond; diamonds (cards)",
"meaning_raw": "💎 diamond; ♦️ diamonds (cards)",
"audio_url": "https://audio.pealim.com/v0/2n/2ng3y19ptzo6.mp3",
"audio_file": "יהלום.mp3",
@ -778091,7 +778091,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ yacht",
"meaning": "yacht",
"meaning_raw": "🛥️ yacht",
"audio_url": "https://audio.pealim.com/v0/fn/fnqancplf3p9.mp3",
"audio_file": "יכטה.mp3",
@ -927031,7 +927031,7 @@
],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "ability, fitness, capability; ️ physical fitness",
"meaning": "ability, fitness, capability; physical fitness",
"meaning_raw": "ability, fitness, capability; 🏋️ physical fitness",
"audio_url": "https://audio.pealim.com/v0/15/15dggrlz3ui39.mp3",
"audio_file": "כושר.mp3",
@ -1003336,7 +1003336,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "‍️ meditation",
"meaning": "meditation",
"meaning_raw": "🧘‍♂️ meditation",
"audio_url": "https://audio.pealim.com/v0/3w/3wecs1tujod3.mp3",
"audio_file": "מדיטציה.mp3",
@ -1019869,7 +1019869,7 @@
],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ recycling",
"meaning": "recycling",
"meaning_raw": "♻️ recycling",
"audio_url": "https://audio.pealim.com/v0/1y/1y0idioumf0oj.mp3",
"audio_file": "מיחזור.mp3",
@ -1107382,7 +1107382,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ sunglasses",
"meaning": "sunglasses",
"meaning_raw": "🕶️ sunglasses",
"audio_url": "https://audio.pealim.com/v0/18/18evs0abnwrg0.mp3",
"audio_file": "משקפי שמש.mp3",
@ -1384284,7 +1384284,7 @@
],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ scissors",
"meaning": "scissors",
"meaning_raw": "✂️ scissors",
"audio_url": "https://audio.pealim.com/v0/gl/gllnqtowivaa.mp3",
"audio_file": "מספריים.mp3",
@ -1451640,7 +1451640,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ spider",
"meaning": "spider",
"meaning_raw": "🕷️ spider",
"audio_url": "https://audio.pealim.com/v0/1u/1umo4y75g98kf.mp3",
"audio_file": "עכביש.mp3",
@ -1451701,7 +1451701,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "mouse ️",
"meaning": "mouse",
"meaning_raw": "mouse 🐀🖱️",
"audio_url": "https://audio.pealim.com/v0/eu/euem3vbl9inl.mp3",
"audio_file": "עכבר.mp3",
@ -1548300,7 +1548300,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ park",
"meaning": "park",
"meaning_raw": "🏞️ park",
"audio_url": "https://audio.pealim.com/v0/fb/fb2nrwhv75ib.mp3",
"audio_file": "פארק.mp3",
@ -1597759,7 +1597759,7 @@
"root": [],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ pepper",
"meaning": "pepper",
"meaning_raw": "🌶️ pepper",
"audio_url": "https://audio.pealim.com/v0/1w/1wnt7hycmb6re.mp3",
"audio_file": "פלפל.mp3",
@ -1891786,7 +1891786,7 @@
],
"pos": "Noun",
"pos_hebrew": "שֵׁם עֶצֶם",
"meaning": "️ slide projector; radiator; barrel jacket (weaponry)",
"meaning": "slide projector; radiator; barrel jacket (weaponry)",
"meaning_raw": "📽️ slide projector; radiator; barrel jacket (weaponry)",
"audio_url": "https://audio.pealim.com/v0/ur/urcm907agh5r.mp3",
"audio_file": "מקרן.mp3",

2
pealim_list_scrape.py
View file

@ -82,7 +82,7 @@ BINYAN_HEBREW: dict[str, str] = {
# Regex for extracting emoji characters
EMOJI_RE = re.compile(
r"[\U0001F300-\U0001FFFF\U00002600-\U000027BF\U0001F000-\U0001F9FF\u2600-\u26FF\u2700-\u27BF]+",
r"[\U0001F300-\U0001FFFF\U00002600-\U000027BF\U0001F000-\U0001F9FF\u2600-\u26FF\u2700-\u27BF\uFE0E\uFE0F\u200D]+",
re.UNICODE,
)

2
release.py
View file

@ -24,7 +24,7 @@ sys.path.insert(0, "/home/node/projects")
import load_keeshare
REPO_API = "https://git.nevo.engineer/api/v1/repos/nevo/hebrew_flash_cards"
FORGEJO_TOKEN: str = load_keeshare.get_entry("git.nevo.engineer")["API_TOKEN"]
FORGEJO_TOKEN: str = load_keeshare.get_entry("git.nevo.engineer")["password"]
OUTPUT_DIR = Path(__file__).parent / "output"
# All deck variants to include in release