render dpd from db

Author: gambhiro

.gitignore

@@ -1,6 +1,8 @@
 appdata.sqlite3
 *.log
 tests/data/assets/
+node_modules/
+profile_time_chart.png
 
 # build folders
 build/

Makefile

@@ -34,3 +34,9 @@ bootstrap-db:
 
 count-code:
 	tokei --type Python --exclude simsapa/assets/ --exclude simsapa/keyboard/ --exclude simsapa/app/lookup.py . | grep -vE '===|Total'
+
+simsapa.js:
+	npx webpack
+
+profile_time_chart.png:
+	@gnuplot < scripts/profile_time_chart.gp

package-lock.json

@@ -0,0 +1,16 @@
+{
+  "name": "simsapa",
+  "version": "0.1.0",
+  "description": "A sutta reader and Pali dictionary application.",
+  "main": "",
+  "scripts": {},
+  "author": "Gambhiro",
+  "license": "GPLv3",
+  "devDependencies": {
+    "sass": "^1.69.5",
+    "ts-loader": "^9.5.1",
+    "typescript": "^5.3.3",
+    "webpack": "^5.89.0",
+    "webpack-cli": "^5.1.4"
+  }
+}

package.json

@@ -89,6 +89,8 @@ tantivy = { git = "https://github.com/simsapa/tantivy-py.git", branch = "simsapa
 # tantivy = { git = "https://github.com/simsapa/tantivy-py.git", branch = "simsapa", rev = "229c10213b32de3ad4c905c2e968798f693afc28" }
 # tantivy = { path = "../libs-src/tantivy-py-simsapa", develop = true }
 # tantivy = { path = "../libs-src/tantivy-py-simsapa/target/wheels/tantivy-0.20.2rc4-cp311-cp311-manylinux_2_34_x86_64.whl" }
+colorama = "^0.4.6"
+blessings = "^1.7"
 
 [tool.poetry.scripts]
 simsapa = 'simsapa.runner:main'

poetry.lock

@@ -146,7 +146,6 @@ def main():
 
     multi_refs.populate_sutta_multi_refs(appdata_db, limit)
 
-    # FIXME improve synonym parsing
     populate_dict_words_from_stardict(appdata_db, stardict_base_path, ignore_synonyms=True, limit=limit)
 
     # === All dict words are added above ===

pyproject.toml

@@ -26,6 +26,8 @@
     logger.error("Missing env variable: BOOTSTRAP_ASSETS_DIR")
     sys.exit(1)
 
+assert(s is not None)
+
 bootstrap_assets_dir = Path(s)
 
 CST4_DIR = bootstrap_assets_dir.joinpath('cst4')
@@ -1178,6 +1180,7 @@ def _parse_path(p: Path) -> Am.Sutta:
         title_ascii = title_ascii,
         uid = uid,
         sutta_ref = uid,
+        nikaya = helpers.uid_to_nikaya(uid),
         language = lang,
         content_html = body,
         content_plain = compact_rich_text(body),
@@ -1288,6 +1291,7 @@ def group_to_sutta(g: Group) -> Am.Sutta:
         title_pali = consistent_nasal_m(g.title),
         uid = uid,
         sutta_ref = helpers.uid_to_ref(ref),
+        nikaya = helpers.uid_to_nikaya(ref),
         language = lang,
         content_html = content_html,
         content_plain = compact_rich_text(content_html),

scripts/bootstrap_appdata.py

@@ -67,6 +67,7 @@ def parse_sutta(p: Path) -> Am.Sutta:
         title_pali = '',
         uid = uid,
         sutta_ref = helpers.uid_to_ref(ref),
+        nikaya = helpers.uid_to_nikaya(ref),
         language = lang,
         content_html = content_html,
         content_plain = compact_rich_text(content_html),

scripts/cst4.py

@@ -86,6 +86,7 @@ def parse_sutta(ref: str, content_html: str) -> Am.Sutta:
         title_pali = title_pali,
         uid = uid,
         sutta_ref = helpers.uid_to_ref(ref),
+        nikaya = helpers.uid_to_nikaya(ref),
         language = lang,
         content_html = content_html,
         content_plain = compact_rich_text(content_html),

scripts/dhammapada_munindo.py

@@ -16,7 +16,7 @@
 from simsapa import logger
 
 import helpers
-from simsapa.app.helpers import consistent_nasal_m, compact_rich_text, pali_to_ascii
+from simsapa.app.helpers import consistent_nasal_m, compact_rich_text
 from simsapa.app.lookup import DHP_CHAPTERS_TO_RANGE
 from simsapa.app.types import QueryType
 
@@ -127,7 +127,6 @@ def parse_sutta(p: Path) -> Am.Sutta:
     title = title.replace(' ', '')
     title = title.replace('&', 'and')
     title = consistent_nasal_m(title)
-    title_ascii = pali_to_ascii(title)
 
     if '/Ud/' in f"{p}":
         # 2 Appāyuka Sutta | Short-lived
@@ -159,6 +158,7 @@ def parse_sutta(p: Path) -> Am.Sutta:
         title_pali = title_pali,
         uid = uid,
         sutta_ref = helpers.uid_to_ref(ref),
+        nikaya = helpers.uid_to_nikaya(ref),
         language = lang,
         content_html = content_html,
         content_plain = compact_rich_text(content_html),

scripts/dhammapada_tipitaka_net.py

@@ -0,0 +1,7 @@
+#!/usr/bin/env python3
+
+def main():
+    pass
+
+if __name__ == "__main__":
+    main()

scripts/dhammatalks_org.py

@@ -37,7 +37,7 @@ def get_simsapa_db(db_path: Path, schema: DbSchemaName, remove_if_exists: bool)
     if remove_if_exists and db_path.exists():
         db_path.unlink()
 
-    find_or_create_db(db_path, schema.value)
+    find_or_create_db(db_path, schema)
 
     try:
         # Create an in-memory database
@@ -47,8 +47,12 @@ def get_simsapa_db(db_path: Path, schema: DbSchemaName, remove_if_exists: bool)
 
         if schema == DbSchemaName.AppData:
             db_conn.execute(text(f"ATTACH DATABASE '{db_path}' AS appdata;"))
-        else:
+        elif schema == DbSchemaName.UserData:
             db_conn.execute(text(f"ATTACH DATABASE '{db_path}' AS userdata;"))
+        elif schema == DbSchemaName.Dpd:
+            db_conn.execute(text(f"ATTACH DATABASE '{db_path}' AS dpd;"))
+        else:
+            raise Exception(f"Unknown schema_name: {schema}")
 
         Session = sessionmaker(engine)
         Session.configure(bind=engine)
@@ -78,6 +82,10 @@ def uid_to_ref(uid: str) -> str:
 
     return uid
 
+def uid_to_nikaya(uid: str) -> str:
+    '''sn12.23 to sn'''
+    nikaya = re.sub(r'^([a-z]+).*', r'\1', uid)
+    return nikaya
 
 def text_to_multi_ref(collection: str, ref_text: str, schema: DbSchemaName) -> Optional[UMultiRef]:
     ref_text = ref_text.lower()
@@ -133,13 +141,15 @@ def text_to_multi_ref(collection: str, ref_text: str, schema: DbSchemaName) -> O
                 edition = "1st ed. Feer (1884)",
             )
 
-        else:
+        elif schema == DbSchemaName.UserData:
             item = Um.MultiRef(
                 collection = collection,
                 ref_type = "pts",
                 ref = normalize_sutta_ref(ref_text),
                 edition = "1st ed. Feer (1884)",
             )
+        else:
+            raise Exception("Only appdata and userdata schema are allowed.")
 
         return item
 
@@ -154,14 +164,17 @@ def text_to_multi_ref(collection: str, ref_text: str, schema: DbSchemaName) -> O
                 edition = "2nd ed. Somaratne (1998)",
             )
 
-        else:
+        elif schema == DbSchemaName.UserData:
             item = Um.MultiRef(
                 collection = collection,
                 ref_type = "pts",
                 ref = normalize_sutta_ref(ref_text),
                 edition = "2nd ed. Somaratne (1998)",
             )
 
+        else:
+            raise Exception("Only appdata and userdata schema are allowed.")
+
         return item
 
     refs = []
@@ -184,13 +197,16 @@ def text_to_multi_ref(collection: str, ref_text: str, schema: DbSchemaName) -> O
                 ref = ", ".join(refs),
             )
 
-        else:
+        elif schema == DbSchemaName.UserData:
             item = Um.MultiRef(
                 collection = collection,
                 ref_type = "pts",
                 ref = ", ".join(refs),
             )
 
+        else:
+            raise Exception("Only appdata and userdata schema are allowed.")
+
         return item
 
     # Ref may contain roman numerals.
@@ -210,13 +226,16 @@ def text_to_multi_ref(collection: str, ref_text: str, schema: DbSchemaName) -> O
                 ref = ", ".join(refs),
             )
 
-        else:
+        elif schema == DbSchemaName.UserData:
             item = Um.MultiRef(
                 collection = collection,
                 ref_type = "pts",
                 ref = ", ".join(refs),
             )
 
+        else:
+            raise Exception("Only appdata and userdata schema are allowed.")
+
         return item
 
     return None

scripts/dpd.py

@@ -64,6 +64,7 @@ def parse_sutta(p: Path) -> Am.Sutta:
         title_pali = '',
         uid = uid,
         sutta_ref = helpers.uid_to_ref(ref),
+        nikaya = helpers.uid_to_nikaya(ref),
         language = lang,
         content_html = content_html,
         content_plain = compact_rich_text(content_html),

scripts/helpers.py

@@ -0,0 +1,39 @@
+set key off
+
+set terminal png size 1500,600
+# set terminal pngcairo size 1200,500 enhanced font 'Helvetica,15'
+set output 'profile_time_chart.png'
+
+# set xlabel "Time"
+set ylabel "Δt since last point"
+
+set yrange [0:]
+set xrange [0:]
+set datafile separator "\t"
+
+set xtics out nomirror
+
+set style fill solid
+
+#set xtics time format "%tM:%.3tS"
+#set xtics rotate by 90 offset 0.0,-4.5
+#set bmargin 20
+
+set xtics time format "%tM:%S"
+set xtics rotate by 90 offset 0.0,-2.5
+set bmargin 17
+
+## Evenly spaced bars.
+# set boxwidth 0.2
+# plot "profile_time.dat" using ($0+0.25):1:xtic(2) with boxes notitle, \
+#      '' using ($0+0.25):1:1 with labels offset 0.5,0.5 notitle
+
+# X axis is elapsed total time.
+# Y axis is a box plot, delta time since last point.
+# Place delta time number above the box.
+# Drop the delta time label if it is 0, by replacing it with an invalid value 1/0.
+# Place the label text under the X axis.
+set boxwidth 0.5
+plot "profile_time.dat" using 1:2 with boxes notitle, \
+     '' using 1:($2 != 0 ? $2 : 1/0):2 with labels offset 0.5,1.0 font ',12' notitle, \
+     '' using 1:($2 != 0 ? 0 : 0):3 with labels right offset 0.0,-5.0 rotate by 90 font ',10' notitle

scripts/nyanadipa.py

@@ -102,6 +102,7 @@ def get_gretil_suttas(limit: Optional[int] = None) -> List[Am.Sutta]:
             title_pali = "",
             uid = uid,
             sutta_ref = "",
+            nikaya = "",
             language = lang,
             content_html = content_html,
             content_plain = compact_rich_text(content_html),
@@ -136,7 +137,8 @@ def populate_from_sanskrit_to_appdata(sanskrit_db: Session, appdata_db: Session)
         for i in res:
             sanskrit_db.expunge(i)
             make_transient(i)
-            i.id = None
+            # Cannot assign member "id" for type "Sutta"
+            # i.id = None
 
             appdata_db.add(i)
         appdata_db.commit()