feat: color themes, dark mode, HC/sepia themes, moon tooltip, docs update
This commit is contained in:
catarrh committed
1 parent
857adce5da
commit
f45791579b
16 files changed
+389
-240
No files matched your search
@@ -12,14 +12,14 @@ CIds are identifiers for saints, feasts, and liturgical elements. They follow th
|
||||
| `02XX-02ZZ` | `02.json` | `023456`, `027890` | February saints |
|
||||
| ... | ... | ... | ... |
|
||||
| `12XX-12ZZ` | `12.json` | `123456`, `127890` | December saints |
|
||||
| Other CIds | `misc.json` | `772426`, `373`, `868` | Non-month-prefixed |
|
||||
| Other CIds | `misc/{first-digit}.json` | `772426→misc/7.json`, `373→misc/3.json` | Non-month-prefixed |
|
||||
|
||||
### Routing Logic
|
||||
```typescript
|
||||
function bundleFileForCid(cid: string): string {
|
||||
return /^(0[1-9]|1[0-2])\d+/.test(cid)
|
||||
? `${cid.substring(0, 2)}.json`
|
||||
: 'misc.json';
|
||||
: `misc/${cid.charAt(0)}.json`;
|
||||
}
|
||||
```
|
||||
|
||||
@@ -79,7 +79,7 @@ function bundleFileForCid(cid: string): string {
|
||||
### Optional Fields
|
||||
- **`name.short`**: Short name variant
|
||||
- **`life.text`**: HTML content (only written when empty)
|
||||
- **`life.id`**: Source identifier (e.g., "minei-0101-772426")
|
||||
- **`life.id`**: Source identifier (e.g., "minei-0101-772426" or "bulgakov-...")
|
||||
- **`life.copyright`**: Copyright string
|
||||
|
||||
## Service Template Structure
|
||||
@@ -121,23 +121,43 @@ function bundleFileForCid(cid: string): string {
|
||||
```
|
||||
|
||||
### Key Characteristics
|
||||
- Generated by `convert-mines.ts` from EPUB source
|
||||
- Generated by `convert-minei.ts` from EPUB source
|
||||
- Stored in `scripts/output/minei.json` (gitignored, 33MB)
|
||||
- Titles and HTML are carefully extracted and parsed
|
||||
- Footnotes collected and appended as "Примечания:" blocks
|
||||
|
||||
## Bulgakov Source Format
|
||||
|
||||
### Format Definition
|
||||
```json
|
||||
{
|
||||
"MM-DD": [
|
||||
{
|
||||
"title": "20-го июля — Св. пророк Илия",
|
||||
"html": "<p>Content paragraphs...</p>"
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
### Key Characteristics
|
||||
- Generated by `convert-bulgakov.ts` from "Настольная книга для священно-церковнослужителей" EPUB
|
||||
- Stored in `scripts/output/bulgakov.json` (gitignored)
|
||||
- Menaion section only (306 days, 332 entries)
|
||||
- Secondary source: fills gaps, never overrides existing Minei content
|
||||
|
||||
## File Organization Rules
|
||||
|
||||
### Lives Files
|
||||
- **Location**: `static/data/{lang}/lives/`
|
||||
- **Files**:
|
||||
- `01.json` through `12.json` (month-prefixed CIds)
|
||||
- `misc.json` (non-month-prefixed CIds)
|
||||
- **Routing**: Based on first two digits of CId
|
||||
- `misc/0.json` through `misc/9.json` (non-month-prefixed CIds, split by first digit)
|
||||
- **Routing**: Based on first two digits of CId (month) or first digit (misc)
|
||||
|
||||
### Menaion Files
|
||||
- **Location**: `static/data/{lang}/menaion/`
|
||||
- **Files**: `01-01.json` through `12-31.json` (daily entries)
|
||||
- **Files**: bundied into `menaion-bundle.json` per language
|
||||
- **Purpose**: Daily liturgical readings by date
|
||||
|
||||
### Service Templates
|
||||
@@ -145,9 +165,15 @@ function bundleFileForCid(cid: string): string {
|
||||
- **Shared**: `static/data/shared/services/templates/`
|
||||
|
||||
### Calendar Data
|
||||
- **Location**: `static/data/{lang}/calendar/` and `static/data/shared/calendar/`
|
||||
- **Location**: `static/data/shared/calendar/`
|
||||
- **Purpose**: Movable feast calculations and metadata
|
||||
|
||||
### Scripture / Paremia Data
|
||||
- **Location**: `static/data/shared/parimii/`
|
||||
- **Monthly files**: `jan/full.json` through `dec/full.json`
|
||||
- **Common files**: `common-saints/full.json`, `cheese-week/full.json`, etc.
|
||||
- **Purpose**: Old Testament readings for Vespers
|
||||
|
||||
## Data Invariants
|
||||
|
||||
### CId Consistency Rules
|
||||
@@ -158,7 +184,7 @@ function bundleFileForCid(cid: string): string {
|
||||
|
||||
### File Organization Invariants
|
||||
- No month file contains CIds with different month prefix
|
||||
- `misc.json` contains all CIds outside the 01-12 prefix range
|
||||
- `misc/{n}.json` contains all CIds with matching first digit
|
||||
- All data files are tracked in `static/data/`
|
||||
|
||||
### Content Validation Invariants
|
||||
@@ -181,7 +207,7 @@ function bundleFileForCid(cid: string): string {
|
||||
- ⚠️ Don't leave trailing commas in JSON
|
||||
|
||||
### File Organization Mistakes
|
||||
- ⚠️ Don't place month-prefixed CIds in misc.json
|
||||
- ⚠️ Don't place month-prefixed CIds in misc files
|
||||
- ⚠️ Don't create inconsistent JSON indentation
|
||||
- ⚠️ Don't mix languages in incorrect directories
|
||||
|
||||
@@ -190,7 +216,7 @@ function bundleFileForCid(cid: string): string {
|
||||
### Valid CId Examples
|
||||
- `010101` → `01.json` (January saint)
|
||||
- `1253` → `12.json` (December saint)
|
||||
- `772426` → `misc.json` (non-prefixed saint)
|
||||
- `772426` → `misc/7.json` (non-prefixed saint)
|
||||
|
||||
### Invalid CId Examples
|
||||
- `00501` → Should not exist (prefix `00` → misc)
|
||||
@@ -198,8 +224,8 @@ function bundleFileForCid(cid: string): string {
|
||||
|
||||
### File Routing Examples
|
||||
- CId `1253` routes to `12.json`
|
||||
- CId `772426` routes to `misc.json`
|
||||
- CId `010101` routes to `01.json`
|
||||
- CId `772426` routes to `misc/7.json`
|
||||
- CId `373` routes to `misc/3.json`
|
||||
|
||||
### Bundle Entry Examples
|
||||
```json
|
||||
@@ -232,15 +258,17 @@ function bundleFileForCid(cid: string): string {
|
||||
|
||||
### Coverage Statistics
|
||||
- Total CIds: 3046
|
||||
- Lives with text: 1190 (39% coverage)
|
||||
- Empty lives: 1856 (61% remain)
|
||||
- Lives with text: 1203 (39% coverage)
|
||||
- Sources: Chetyi-Minei (1190) + Bulgakov (13)
|
||||
- Empty lives: 1843 (61% remain)
|
||||
|
||||
### Data Files
|
||||
- Total validated files: 274
|
||||
- Main source files: 6 Lives bundle files (misc, 01-12)
|
||||
- Lives bundle files: 12 month files (01-12) + 10 misc split files (0-9)
|
||||
- Service template files: Multiple per language
|
||||
- Parimii files: 12 monthly + common saints + triodion periods
|
||||
|
||||
### Recent Changes
|
||||
- Bundle fix: 868 Иаков Боровицký moved from 05-22 to 10-23
|
||||
- Enrichment: 64 manual fixes added to enrich-lives.ts
|
||||
- Coverage increase: 1009→1190 lives with text (191 new)
|
||||
- Bundle fix: 868 Иаков Боровицкий moved from 05-22 to 10-23
|
||||
- Minei enrichment: 64 manual fixes added
|
||||
- Bulgakov enrichment: 9 manual fixes added, 13 new lives
|
||||
- Coverage increase: 1009→1190→1203 lives with text
|
||||
@@ -4,11 +4,17 @@
|
||||
|
||||
Run enrichment in safe mode first:
|
||||
```bash
|
||||
# Dry run to see matches
|
||||
# Minei dry run
|
||||
npx tsx scripts/enrich-lives.ts
|
||||
|
||||
# Write changes when confident
|
||||
npx tsx scripts/enrich-lates.ts --write
|
||||
# Minei write
|
||||
npx tsx scripts/enrich-lives.ts --write
|
||||
|
||||
# Bulgakov dry run
|
||||
npx tsx scripts/enrich-lives.ts --bulgakov
|
||||
|
||||
# Bulgakov write
|
||||
npx tsx scripts/enrich-lives.ts --bulgakov --write
|
||||
```
|
||||
|
||||
## Common Enrichment Mistakes
|
||||
@@ -31,20 +37,23 @@ npx tsx scripts/enrich-lates.ts --write
|
||||
- ⚠️ Don't append to CIds that already have life.text without checking collision behavior
|
||||
- ⚠️ Don't assume all multi-source CIds follow same pattern
|
||||
|
||||
### Bulgakov-Specific Issues
|
||||
- ⚠️ Bulgakov only covers Menaion (saints by calendar date), not Triodion/Pentecostarion
|
||||
- ⚠️ Bulgakov is secondary source — only fills gaps, never overrides Minei
|
||||
- ⚠️ Some Bulgakov entries are feast descriptions, not saint lives — may have no target CId
|
||||
|
||||
### Validation Skipping
|
||||
- ⚠️ Don't skip `npx tsx scripts/validate-data.ts` — it catches real errors
|
||||
- ⚠️ Don't skip `npx tsc --noEmit` — type errors indicate real problems
|
||||
- ⚠️ Don't skip `npm run build` — build failures need investigation
|
||||
- ⚠️ Don't assume "all files valid" without actually running it
|
||||
- ⚠️ Don't skip data validation — run `validate-data.ts` after changes
|
||||
|
||||
## Decision Points for AI Agents
|
||||
|
||||
### When to Add MANUAL_FIXES
|
||||
- When score is 0.35-0.6 and you can identify the correct target
|
||||
- When source title contains distinctive substring not in other titles on same date
|
||||
- When auto-matcher picks wrong saint (e.g., different homonym on same date)
|
||||
- When target CId exists but is listed on wrong calendar date (bundle bug)
|
||||
- When narrative maps to known CId but has empty life (can be enriched)
|
||||
- When Bulgakov title contains distinctive substring not in Minei titles
|
||||
|
||||
### When to Leave Unmatched
|
||||
- When source is a narrative or homily without saint association
|
||||
@@ -60,7 +69,7 @@ npx tsx scripts/enrich-lates.ts --write
|
||||
## Quality Checkpoints
|
||||
|
||||
### After Manual Fixes Addition
|
||||
- Verify substring uniqueness per date (use verification script)
|
||||
- Verify substring uniqueness per date
|
||||
- Check that target CIds exist and are empty
|
||||
- Re-run dry run to verify improvement
|
||||
- Check for potential new conflicts with existing fixes
|
||||
@@ -72,9 +81,9 @@ npx tsx scripts/enrich-lates.ts --write
|
||||
- Verify no unintended side effects on other files
|
||||
|
||||
### Before Committing
|
||||
- Run full validation: `npx tsx scripts/validate-data.ts`
|
||||
- Type check: `npx tsc --noEmit`
|
||||
- Build verify: `npm run build`
|
||||
- Run data validation: `npx tsx scripts/validate-data.ts`
|
||||
- Check git status to confirm intended files staged
|
||||
|
||||
## Troubleshooting Common Issues
|
||||
@@ -105,25 +114,20 @@ npx tsx scripts/enrich-lates.ts --write
|
||||
- ⚠️ **Expected behavior**: First source writes without heading, subsequent sources append
|
||||
- **Check**: Verify total chapters match expected count for CId
|
||||
|
||||
### Strange JSON Syntax Errors
|
||||
- **Problem**: Parse errors in data files after modification
|
||||
- **Solution**: Check JSON syntax, fix trailing commas, quote issues
|
||||
- **Verify**: Run `validate-data.ts` to get specific error location
|
||||
|
||||
### Build Size Changes
|
||||
- **Problem**: Unexpected file size increases/decreases
|
||||
- **Solution**: Check for malformed content, duplicate data, formatting changes
|
||||
- **Check**: Compare before/after file sizes in git diff
|
||||
### Bulgakov-Specific Issues
|
||||
- **Problem**: Bulgakov entry has no matching CId
|
||||
- **Solution**: Check if it's a feast day description (not a saint life)
|
||||
- **Alternative**: Search lives-index.json for the saint's name
|
||||
- **Check**: Verify the date has the correct CIds in the menaion bundle
|
||||
|
||||
## Verification Commands
|
||||
|
||||
### Coverage Tracking
|
||||
```bash
|
||||
# Check coverage statistics
|
||||
python3 -c "
|
||||
import json, glob, os
|
||||
total=has=0
|
||||
for fp in glob.glob('static/data/ru/lives/*.json'):
|
||||
for fp in sorted(glob.glob('static/data/ru/lives/*.json') + glob.glob('static/data/ru/lives/misc/*.json')):
|
||||
data=json.load(open(fp))
|
||||
for cid,entry in data.items():
|
||||
total+=1
|
||||
@@ -135,14 +139,15 @@ print(f'Coverage: {has}/{total} ({has*100//total}%) lives with text')
|
||||
|
||||
### Collision Chapter Count Check
|
||||
```bash
|
||||
# Check collision targets have correct chapter counts
|
||||
python3 -c "
|
||||
import json, re
|
||||
misc = json.load(open('static/data/ru/lives/misc.json'))
|
||||
for cid in ['493', '1674', '257401']: # Known collision targets
|
||||
text = misc[cid]['life']['text']
|
||||
headings = re.findall(r'<b>([^<]+)</b>', text)
|
||||
print(f'{cid}: {len(headings)} chapters')
|
||||
for fp in ['static/data/ru/lives/misc/4.json', 'static/data/ru/lives/misc/1.json']:
|
||||
data = json.load(open(fp))
|
||||
for cid in ['493', '1674', '257401']:
|
||||
if cid in data:
|
||||
text = data[cid]['life']['text']
|
||||
headings = re.findall(r'<b>([^<]+)</b>', text)
|
||||
print(f'{cid}: {len(headings)} chapters')
|
||||
"
|
||||
```
|
||||
|
||||
@@ -159,21 +164,22 @@ npx tsx scripts/tools/stats.ts --lang ru
|
||||
## Recent Context Updates
|
||||
|
||||
### Known Fixed Issues
|
||||
- 868 Иаков Боровицký moved from 05-22 to 10-23 (bundle mis-mapping correction)
|
||||
- 868 Иаков Боровицкий moved from 05-22 to 10-23 (bundle mis-mapping correction)
|
||||
- Сретение→373 added (02-02 Сказание about Presentation)
|
||||
- Захарий Печерский→822 added (03-24 miracle story)
|
||||
- Анна пророчица→2396 added (08-28 prophetess Anna)
|
||||
|
||||
### Current Unmatched Floor
|
||||
- 27 entries remain unmatched (all narratives/homilies or already-filled targets)
|
||||
- These are at the floor for Chetyi-Minei source — no recoverable matches available
|
||||
- **Minei**: 27 entries remain unmatched (all narratives/homilies or already-filled targets)
|
||||
- **Bulgakov**: 121 entries unmatched (no recoverable targets — saints already have lives or no CId)
|
||||
- These are at the floor for both sources — no recoverable matches available
|
||||
|
||||
## File Routing Quick Reference
|
||||
|
||||
### Lives File Routing
|
||||
- Files: `static/data/ru/lives/01.json` through `12.json` for month-prefixed CIds
|
||||
- File: `misc.json` for non-month-prefixed CIds
|
||||
- Route: `bundleFileForCid(cid: string):` checks `/^(0[1-9]|1[0-2])\d+/.test(cid)`
|
||||
- Files: `static/data/ru/lives/misc/0.json` through `9.json` for non-month-prefixed CIds
|
||||
- Route: `bundleFileForCid(cid)` checks `/^(0[1-9]|1[0-2])\d+/.test(cid)`
|
||||
|
||||
### Bundle File Organization
|
||||
- Main bundle: `static/data/cu/menaion-bundle.json` (authoritative calendar)
|
||||
@@ -188,14 +194,14 @@ npx tsx scripts/tools/stats.ts --lang ru
|
||||
- Confirm coverage increased as expected
|
||||
|
||||
### Documentation Updates
|
||||
- Update DATA_FORMAT.md or DATA_RUS.md if schema changed
|
||||
- Update DATA_EN.md or DATA_RUS.md if schema changed
|
||||
- Update coverage statistics in relevant documentation
|
||||
- Add new manual fixes to enrichment documentation if needed
|
||||
|
||||
### Commit Sequence
|
||||
```bash
|
||||
# 1. Validate, typecheck, build all passing
|
||||
npx tsx scripts/validate-data.ts && npx tsc --noEmit && npm run build
|
||||
# 1. Typecheck, build, validate all passing
|
||||
npx tsc --noEmit && npm run build && npx tsx scripts/validate-data.ts
|
||||
|
||||
# 2. Stage all changes
|
||||
git add scripts/enrich-lives.ts scripts/output/lives-match-report.json static/data/ru/lives/
|
||||
@@ -208,20 +214,19 @@ git commit -m "enrich [N] more ru lives: [description]"
|
||||
|
||||
### Current Status
|
||||
- Total CIds: 3046
|
||||
- Lives with text: 1190 (enriched from Chetyi-Minei)
|
||||
- Unmatched minei chapters: 27 (floor: narratives, no-target, already-filled)
|
||||
- Files validated: 274 files (all passing)
|
||||
- Lives with text: 1203 (enriched from Chetyi-Minei + Bulgakov)
|
||||
- Unmatched Minei: 27 (floor: narratives, no-target, already-filled)
|
||||
- Unmatched Bulgakov: 121 (floor: no recoverable targets)
|
||||
|
||||
### Recent Enrichment Work
|
||||
- Baseline: 1009 lives with text (from prior work)
|
||||
- Latest commits added 181 lives (121 + 57 + 3)
|
||||
- Manual fixes added: 214 total in enrich-lives.ts
|
||||
- Bundle corrections applied: 868 date fix
|
||||
### Sources
|
||||
- **Chetyi-Minei**: 1190 lives, 64 manual fixes, 27 unmatched at floor
|
||||
- **Bulgakov Desktop Book**: 13 lives, 9 manual fixes, 121 unmatched at floor
|
||||
- **Total coverage**: 1203/3046 (39%)
|
||||
|
||||
### Progress Tracking
|
||||
- Review band: 127 entries resolved, 0 remaining
|
||||
- Unmatched band: 94 → 30 → 27 (final floor)
|
||||
- Coverage: 1009→1130→1190 lives (181 net increase)
|
||||
- Minei band: 94 → 30 → 27 (final floor)
|
||||
- Bulgakov: 332 entries processed, 13 new lives, 121 unmatched
|
||||
- Coverage: 1009→1130→1190→1203 (194 net increase)
|
||||
|
||||
## Example Workflow for Adding Manual Fixes
|
||||
|
||||
@@ -240,12 +245,11 @@ Target: 822 (Прп. Захарий Печерский, EMPTY) - correct saint
|
||||
|
||||
### Step 3: Verify Uniqueness
|
||||
```bash
|
||||
# Check if substring is unique on date 03-24
|
||||
python3 -c "
|
||||
import json, re
|
||||
m=json.load(open('scripts/output/minei.json'))
|
||||
titles=[t['title'] for t in m['03-24']]
|
||||
cnt=sum(1 for t in titles if 'воспоминание о чуде' in re.sub(r'\s+',' ',t['title']).lower())
|
||||
cnt=sum(1 for t in titles if 'воспоминание о чуде' in re.sub(r'\s+',' ',t).lower())
|
||||
print(f'Count: {cnt}')
|
||||
"
|
||||
```
|
||||
|
||||
@@ -5,44 +5,45 @@
|
||||
**Ponomar** is a Progressive Web App for Orthodox Church calendar, liturgical services, and Bible readings.
|
||||
|
||||
- **Technology**: TypeScript + Vite + Tailwind CSS v4
|
||||
- **Data**: JSON-based liturgical data organized by language (en, cu, el, fr, zh, ru)
|
||||
- **Data**: JSON-based liturgical data organized by language (en, cu, ru)
|
||||
- **Architecture**: Client-side PWA with static JSON data, no backend database
|
||||
- **Core Functionality**: Calendar display, service assembly, Bible reading, saint lives
|
||||
- **Core Functionality**: Calendar display, service assembly, Bible reading, saint lives, astronomy
|
||||
|
||||
## Key Architectural Patterns
|
||||
|
||||
### Data Organization
|
||||
- **Language-based structure**: `static/data/{lang}/` (en, cu, el, fr, zh, ru)
|
||||
- **Bundle system**: menaion-bundles, lives bundles, service templates
|
||||
- **File routing**: CIds with `01`-`12` prefix → month files, else `misc.json`
|
||||
- **Language-based structure**: `static/data/{lang}/` (en, cu, ru)
|
||||
- **Bundle system**: menaion-bundles, lives bundles (month-prefixed + misc split), service templates
|
||||
- **File routing**: CIds with `01`-`12` prefix → month files, else `misc/{first-digit}.json`
|
||||
|
||||
### Core Scripts
|
||||
- `convert-all.ts` — Master conversion script
|
||||
- `enrich-lives.ts` — Fuzzy matching and enrichment pipeline
|
||||
- `validate-data.ts` — Main validator (checks 274 files)
|
||||
- `convert-minei.ts` — Chetyi-Minei EPUB to JSON conversion
|
||||
- `migrate-data.ts` — Data normalization
|
||||
- `convert-services.ts` — Service XML to JSON conversion
|
||||
- `enrich-lives.ts` — Fuzzy matching and enrichment pipeline (Chetyi-Minei + Bulgakov)
|
||||
- `validate-data.ts` — Main validator
|
||||
- `convert-bulgakov.ts` — Bulgakov's Desktop Book EPUB to JSON conversion
|
||||
|
||||
## Recent Work Context
|
||||
|
||||
### Completed Enrichment
|
||||
- **Chetyi-Minei import**: 1154 chapters processed, 1190/3046 lives enriched
|
||||
- **Manual fixes**: 214 manual corrections in `enrich-lives.ts`
|
||||
- **Bundle fixes**: 868 Иаков Боровицký corrected from 05-22 to 10-23
|
||||
- **Coverage**: 39% of lives have texts (source from Chetyi-Minei)
|
||||
- **Chetyi-Minei import**: 1154 chapters processed, 1190 lives enriched
|
||||
- **Bulgakov import**: 332 entries from "Настольная книга" Menaion section, 13 new lives enriched
|
||||
- **Manual fixes**: 224 manual corrections in `enrich-lives.ts` (64 Minei + 9 Bulgakov + others)
|
||||
- **Bundle fixes**: 868 Иаков Боровицкий corrected from 05-22 to 10-23
|
||||
- **Coverage**: 1203/3046 lives have texts (sources: Chetyi-Minei + Bulgakov)
|
||||
|
||||
### Validation Status
|
||||
- All data files validated: 274 files checked
|
||||
- All data files validated
|
||||
- TypeScript compiles cleanly
|
||||
- Build succeeds without errors
|
||||
|
||||
## Critical Invariants
|
||||
|
||||
- **Never overwrite existing `life.text`** — enrichment only fills empty entries
|
||||
- **Bulgakov is secondary source** — fills gaps, never overrides Minei
|
||||
- **File routing is strict**: CId prefix determines file location
|
||||
- **Bundle CIds must exist**: Menaion CIds require corresponding lives entries
|
||||
- **Static data is tracked**: `static/data/` in git (except `scripts/output/minei.json`)
|
||||
- **Validation must pass**: Changes must pass `validate-data.ts`, `tsc --noEemit`, `npm run build`
|
||||
- **Validation must pass**: Changes must pass `tsc --noEmit`, `npm run build`
|
||||
|
||||
## Key Script Quick Reference
|
||||
|
||||
@@ -51,74 +52,64 @@
|
||||
npm run dev # Start dev server
|
||||
npm run build # Production build
|
||||
|
||||
# Data operations
|
||||
npm run convert # Convert XML to JSON
|
||||
npm run migrate # Normalize data format
|
||||
|
||||
# Validation
|
||||
npx tsx scripts/validate-data.ts # Main validator
|
||||
npx tsc --noEmit # Type checking
|
||||
npm run build # Build verification
|
||||
npx tsx scripts/validate-data.ts # Main validator
|
||||
|
||||
# Enrichment
|
||||
npx tsx scripts/enrich-lives.ts # Dry run enrichment
|
||||
npx tsx scripts/enrich-lives.ts --write # Apply enrichment
|
||||
# Enrichment (Minei)
|
||||
npx tsx scripts/enrich-lives.ts # Dry run
|
||||
npx tsx scripts/enrich-lives.ts --write # Apply
|
||||
|
||||
# Enrichment (Bulgakov)
|
||||
npx tsx scripts/enrich-lives.ts --bulgakov # Dry run
|
||||
npx tsx scripts/enrich-lives.ts --bulgakov --write
|
||||
```
|
||||
|
||||
## File Structure Highlights
|
||||
|
||||
```
|
||||
src/
|
||||
├── core/ # Domain logic (calendar, paschalion, service assembly)
|
||||
├── core/ # Domain logic (calendar, paschalion, service assembly, astronomy)
|
||||
├── ui/ # View components
|
||||
└── main.ts # Entry point
|
||||
|
||||
scripts/
|
||||
├── convert-*.ts # XML→JSON conversion pipeline
|
||||
├── validate-*.ts # Comprehensive validation suite
|
||||
└── enrich-lives.ts # Enrichment with manual fixes
|
||||
├── convert-*.ts # XML/EPUB → JSON conversion pipeline
|
||||
├── validate-*.ts # Comprehensive validation suite
|
||||
└── enrich-lives.ts # Enrichment with manual fixes (Minei + Bulgakov)
|
||||
|
||||
static/data/
|
||||
├── cu/ # Church Slavonic (authoritative calendar)
|
||||
├── ru/ # Russian (enriched lives)
|
||||
├── en/ # English
|
||||
└── shared/ # Cross-language resources
|
||||
├── en/ # English (enriched lives + service texts)
|
||||
└── shared/ # Cross-language resources (calendar, lives index, parimii)
|
||||
```
|
||||
|
||||
## Important Notes
|
||||
|
||||
### Pipeline Dependencies
|
||||
- **Chetyi-Minei source**: EPUB conversion requires `convert-minei.ts`
|
||||
- **Enrichment workflow**: Requires minei.json output + menaion-bundle.json
|
||||
- **Validation chain**: Each commit must pass validation → typecheck → build
|
||||
- **Bulgakov source**: EPUB conversion requires `convert-bulgakov.ts`
|
||||
- **Enrichment workflow**: Requires minei.json + bulgakov.json + menaion-bundle.json
|
||||
- **Validation chain**: Each commit must pass typecheck → build
|
||||
|
||||
### File System Constraints
|
||||
- `scripts/output/minei.json` is gitignored (33MB source file)
|
||||
- `scripts/output/bulgakov.json` is gitignored
|
||||
- `static/data/` is fully tracked in git
|
||||
- Lives files are written by month (01.json-12.json) or misc.json
|
||||
|
||||
## Common Tools Reference
|
||||
|
||||
- **Search**: `npx tsx scripts/tools/search-texts.ts <query>`
|
||||
- **Stats**: `npx tsx scripts/tools/stats.ts [--lang en]`
|
||||
- **Validate**: `npx tsx scripts/validate-data.ts`
|
||||
|
||||
## Documentation Reference
|
||||
|
||||
- **DATA_FORMAT.md** — Detailed technical specifications (English)
|
||||
- **DATA_RUS.md** — Complete documentation in Russian
|
||||
- **README.md** — Project overview and getting started
|
||||
|
||||
## Working Reminders
|
||||
|
||||
- Always run validation before committing data changes
|
||||
- Check coverage statistics when working with enrichment
|
||||
- Test builds after any modifications to static data
|
||||
- Review the match report after dry runs
|
||||
- Lives files: month files (01.json-12.json) + misc split (misc/0.json-misc/9.json)
|
||||
|
||||
## Current State
|
||||
|
||||
- Total CIds: 3046
|
||||
- Lives with text: 1190 (enriched from Chetyi-Minei)
|
||||
- Unmatched minei chapters: 27 (floor: narratives, no-target, already-filled)
|
||||
- Latest enrichment commits: `ec3f593` (3 more lives), `08950cd` (57 more lives), `381a494` (121 more lives), `7dde216` (baseline enrichment)
|
||||
- Lives with text: 1203 (Chetyi-Minei + Bulgakov)
|
||||
- Unmatched Minei: 27 (floor: narratives, no-target, already-filled)
|
||||
- Unmatched Bulgakov: 121 (all no recoverable targets)
|
||||
- Latest enrichment commits: `e32d787` (Bulgakov), `c342a5b` (orthography), `08950cd` (64 fixes)
|
||||
|
||||
## Documentation Reference
|
||||
|
||||
- **DATA_EN.md** — Detailed technical specifications (English)
|
||||
- **DATA_RUS.md** — Complete documentation in Russian
|
||||
- **README.md** — Project overview and getting started
|
||||
@@ -6,10 +6,11 @@
|
||||
- **CRITICAL**: Never overwrite existing `life.text` fields in lives entries
|
||||
- Enrichment pipeline only fills empty entries
|
||||
- If a target already has content, classify as `already-filled` and skip
|
||||
- **Bulgakov is secondary source**: fills gaps only, never overrides Minei content
|
||||
|
||||
### File Modification Permissions
|
||||
- **Allowed**: Adding new life.text to empty entries
|
||||
- **Allowed**: Adding manual fixes to `enrich-lives.ts` MANUAl_FIXES
|
||||
- **Allowed**: Adding manual fixes to `enrich-lives.ts` MANUAL_FIXES
|
||||
- **Allowed**: Correcting menaion-bundle.json for CId date corrections
|
||||
- **Forbidden**: Modifying existing life.text content
|
||||
- **Forbidden**: Deleting or renaming CIds without proper validation
|
||||
@@ -21,17 +22,17 @@
|
||||
All changes must pass all three checks:
|
||||
|
||||
```bash
|
||||
# 1. Data validation
|
||||
npx tsx scripts/validate-data.ts
|
||||
# Expected: "All files valid!" or specific error count
|
||||
|
||||
# 2. Type safety
|
||||
# 1. Type safety
|
||||
npx tsc --noEmit
|
||||
# Expected: No TypeScript errors
|
||||
|
||||
# 3. Build verification
|
||||
# 2. Build verification
|
||||
npm run build
|
||||
# Expected: Successful build with reasonable bundle sizes
|
||||
|
||||
# 3. Data validation
|
||||
npx tsx scripts/validate-data.ts
|
||||
# Expected: "All files valid!" or specific error count
|
||||
```
|
||||
|
||||
### When to Stop
|
||||
@@ -63,14 +64,13 @@ update [script name]: [brief description]
|
||||
- Be specific about what changed
|
||||
- Reference specific CIds or dates when applicable
|
||||
- Keep messages concise but descriptive
|
||||
- Reference recent commits for style
|
||||
|
||||
## File Change Guidelines
|
||||
|
||||
### Static Data Files
|
||||
- **Tracked**: `static/data/` directory (all JSON files tracked)
|
||||
- **Not tracked**: `scripts/output/minei.json` (33MB generated file)
|
||||
- **Validate**: Always run validation after data changes
|
||||
- **Not tracked**: `scripts/output/minei.json`, `scripts/output/bulgakov.json`
|
||||
- **Validate**: Always run typecheck and build after data changes
|
||||
|
||||
### Script Files
|
||||
- Maintain existing code patterns
|
||||
@@ -119,7 +119,7 @@ update [script name]: [brief description]
|
||||
## Documentation Requirements
|
||||
|
||||
### When Modifying Data Schemas
|
||||
- Update relevant documentation files (DATA_FORMAT.md, DATA_RUS.md)
|
||||
- Update relevant documentation files (DATA_EN.md, DATA_RUS.md)
|
||||
- Note any breaking changes or invariants
|
||||
- Update project README if structural changes
|
||||
|
||||
@@ -152,7 +152,7 @@ update [script name]: [brief description]
|
||||
### Before Starting
|
||||
1. Review existing MANUAL_FIXES in `enrich-lives.ts`
|
||||
2. Understand the current coverage status
|
||||
3. Identify which dates/cases you're targeting
|
||||
3. Identify which source (Minei or Bulgakov) and dates you're targeting
|
||||
|
||||
### During Work
|
||||
1. Use dry runs first: `npx tsx scripts/enrich-lives.ts`
|
||||
@@ -170,8 +170,8 @@ update [script name]: [brief description]
|
||||
## Quality Assurance Standards
|
||||
|
||||
### Coverage Tracking
|
||||
- Monitor coverage statistics: `1190/3046 lives with text`
|
||||
- Track unmatched count: currently 27 (floor for this data source)
|
||||
- Monitor coverage statistics: `1203/3046 lives with text`
|
||||
- Track unmatched counts: 27 Minei + 121 Bulgakov (floor)
|
||||
- Report changes in coverage when adding MANUAL_FIXES
|
||||
|
||||
### Content Verification
|
||||
@@ -198,12 +198,18 @@ const MANUAL_FIXES: Record<string, string> = {
|
||||
|
||||
### Running Enrichment
|
||||
```bash
|
||||
# Dry run
|
||||
# Minei dry run
|
||||
npx tsx scripts/enrich-lives.ts
|
||||
|
||||
# Write changes
|
||||
# Minei write
|
||||
npx tsx scripts/enrich-lives.ts --write
|
||||
|
||||
# Bulgakov dry run
|
||||
npx tsx scripts/enrich-lives.ts --bulgakov
|
||||
|
||||
# Bulgakov write
|
||||
npx tsx scripts/enrich-lives.ts --bulgakov --write
|
||||
|
||||
# Single month
|
||||
npx tsx scripts/enrich-lives.ts --month 01
|
||||
npx tsx scripts/enrich-lives.ts --write --month 01
|
||||
@@ -224,7 +230,7 @@ npx tsx scripts/validate-triodion.ts
|
||||
python3 -c "
|
||||
import json,glob,os
|
||||
total=has=0
|
||||
for fp in glob.glob('static/data/ru/lives/*.json'):
|
||||
for fp in sorted(glob.glob('static/data/ru/lives/*.json') + glob.glob('static/data/ru/lives/misc/*.json')):
|
||||
data=json.load(open(fp))
|
||||
for cid,entry in data.items():
|
||||
total+=1
|
||||
|
||||
Reference in new issue
Block a user