Spaces:
Sleeping
Sleeping
Commit
·
cb87c06
1
Parent(s):
63ae283
els cache with function parameters
Browse files- app.py +82 -28
- els_cache.db +0 -3
- els_cache.db.initial +0 -3
app.py
CHANGED
|
@@ -44,6 +44,20 @@ MAX_PHRASE_LENGTH_LIMIT = 20
|
|
| 44 |
ELS_CACHE_DB = "els_cache.db"
|
| 45 |
DATABASE_TIMEOUT = 60
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
# --- Database Initialization ---
|
| 48 |
def initialize_database():
|
| 49 |
global conn
|
|
@@ -58,7 +72,7 @@ def initialize_database():
|
|
| 58 |
chapter INTEGER,
|
| 59 |
verse INTEGER,
|
| 60 |
phrase_length INTEGER,
|
| 61 |
-
word_position TEXT,
|
| 62 |
PRIMARY KEY (gematria_sum, words, book, chapter, verse, word_position)
|
| 63 |
)
|
| 64 |
''')
|
|
@@ -80,25 +94,53 @@ initialize_database()
|
|
| 80 |
# --- ELS Cache Functions ---
|
| 81 |
def create_els_cache_table():
|
| 82 |
with sqlite3.connect(ELS_CACHE_DB) as conn:
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
return hashlib.sha256(json.dumps(key).encode()).hexdigest()
|
| 93 |
|
| 94 |
|
| 95 |
def cached_process_json_files(func, *args, **kwargs):
|
| 96 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 97 |
|
| 98 |
try:
|
| 99 |
with sqlite3.connect(ELS_CACHE_DB, timeout=DATABASE_TIMEOUT) as conn:
|
| 100 |
cursor = conn.cursor()
|
| 101 |
-
cursor.execute(
|
|
|
|
| 102 |
result = cursor.fetchone()
|
| 103 |
if result:
|
| 104 |
logger.info(f"Cache hit for query: {query_hash}")
|
|
@@ -112,13 +154,15 @@ def cached_process_json_files(func, *args, **kwargs):
|
|
| 112 |
try:
|
| 113 |
with sqlite3.connect(ELS_CACHE_DB, timeout=DATABASE_TIMEOUT) as conn:
|
| 114 |
cursor = conn.cursor()
|
| 115 |
-
cursor.execute("INSERT INTO els_cache (query_hash, results) VALUES (?, ?)",
|
|
|
|
| 116 |
conn.commit()
|
| 117 |
except sqlite3.Error as e:
|
| 118 |
logger.error(f"Database error caching results: {e}")
|
| 119 |
|
| 120 |
return results
|
| 121 |
|
|
|
|
| 122 |
# --- Helper Functions (from Network app.py) ---
|
| 123 |
def flatten_text(text: List) -> str:
|
| 124 |
if isinstance(text, list):
|
|
@@ -130,8 +174,8 @@ def search_gematria_in_db(gematria_sum: int, max_words: int) -> List[Tuple[str,
|
|
| 130 |
with sqlite3.connect(DATABASE_FILE) as conn:
|
| 131 |
cursor = conn.cursor()
|
| 132 |
cursor.execute('''
|
| 133 |
-
SELECT words, book, chapter, verse, phrase_length, word_position
|
| 134 |
-
FROM results
|
| 135 |
WHERE gematria_sum = ? AND phrase_length <= ?
|
| 136 |
''', (gematria_sum, max_words))
|
| 137 |
results = cursor.fetchall()
|
|
@@ -174,40 +218,50 @@ def perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_b
|
|
| 174 |
length = 0
|
| 175 |
|
| 176 |
selected_language_long = tlang # From the Gradio dropdown (long form)
|
| 177 |
-
|
| 178 |
-
|
|
|
|
| 179 |
tlang = "en"
|
| 180 |
-
logger.warning(
|
|
|
|
| 181 |
|
|
|
|
| 182 |
if include_torah:
|
| 183 |
-
logger.debug(
|
| 184 |
-
|
|
|
|
|
|
|
| 185 |
else:
|
| 186 |
results["Torah"] = []
|
| 187 |
|
| 188 |
if include_bible:
|
| 189 |
-
results["Bible"] = cached_process_json_files(bible.process_json_files, 40, 66, step, rounds_combination, length,
|
|
|
|
| 190 |
else:
|
| 191 |
results["Bible"] = []
|
| 192 |
|
| 193 |
if include_quran:
|
| 194 |
-
results["Quran"] = cached_process_json_files(quran.process_json_files, 1, 114, step, rounds_combination, length,
|
|
|
|
| 195 |
else:
|
| 196 |
results["Quran"] = []
|
| 197 |
|
| 198 |
if include_hindu:
|
| 199 |
-
results["Rig Veda"] = cached_process_json_files(
|
|
|
|
| 200 |
else:
|
| 201 |
results["Rig Veda"] = []
|
| 202 |
|
| 203 |
if include_tripitaka:
|
| 204 |
-
results["Tripitaka"] = cached_process_json_files(
|
|
|
|
| 205 |
else:
|
| 206 |
results["Tripitaka"] = []
|
| 207 |
|
| 208 |
return results
|
| 209 |
|
| 210 |
|
|
|
|
| 211 |
def add_24h_projection(results_dict): #Now takes a dictionary of results
|
| 212 |
for book_name, results in results_dict.items(): # Iterate per book
|
| 213 |
num_results = len(results)
|
|
@@ -304,14 +358,14 @@ with gr.Blocks() as app:
|
|
| 304 |
|
| 305 |
with gr.Row():
|
| 306 |
step = gr.Number(label="Jump Width (Steps) for ELS")
|
| 307 |
-
float_step = gr.Number(visible=False, value=1)
|
| 308 |
half_step_btn = gr.Button("Steps / 2")
|
| 309 |
double_step_btn = gr.Button("Steps * 2")
|
| 310 |
-
|
| 311 |
with gr.Column():
|
| 312 |
round_x = gr.Number(label="Round (1)", value=1)
|
| 313 |
round_y = gr.Number(label="Round (2)", value=-1)
|
| 314 |
-
|
| 315 |
rounds_combination = gr.Textbox(label="Combined Rounds", value="1,-1")
|
| 316 |
|
| 317 |
with gr.Row():
|
|
@@ -320,7 +374,7 @@ with gr.Blocks() as app:
|
|
| 320 |
include_quran_chk = gr.Checkbox(label="Include Quran", value=True)
|
| 321 |
include_hindu_chk = gr.Checkbox(label="Include Rigveda", value=False)
|
| 322 |
include_tripitaka_chk = gr.Checkbox(label="Include Tripitaka", value=False)
|
| 323 |
-
|
| 324 |
strip_spaces = gr.Checkbox(label="Strip Spaces from Books", value=True)
|
| 325 |
strip_in_braces = gr.Checkbox(label="Strip Text in Braces from Books", value=True)
|
| 326 |
strip_diacritics_chk = gr.Checkbox(label="Strip Diacritics from Books", value=True)
|
|
|
|
| 44 |
ELS_CACHE_DB = "els_cache.db"
|
| 45 |
DATABASE_TIMEOUT = 60
|
| 46 |
|
| 47 |
+
# --- ELS Cache Functions ---
|
| 48 |
+
def create_els_cache_table():
|
| 49 |
+
if not os.path.exists(ELS_CACHE_DB):
|
| 50 |
+
with sqlite3.connect(ELS_CACHE_DB) as conn:
|
| 51 |
+
conn.execute('''
|
| 52 |
+
CREATE TABLE els_cache (
|
| 53 |
+
query_hash TEXT PRIMARY KEY,
|
| 54 |
+
function_name TEXT,
|
| 55 |
+
args TEXT,
|
| 56 |
+
kwargs TEXT,
|
| 57 |
+
results TEXT
|
| 58 |
+
)
|
| 59 |
+
''')
|
| 60 |
+
|
| 61 |
# --- Database Initialization ---
|
| 62 |
def initialize_database():
|
| 63 |
global conn
|
|
|
|
| 72 |
chapter INTEGER,
|
| 73 |
verse INTEGER,
|
| 74 |
phrase_length INTEGER,
|
| 75 |
+
word_position TEXT,
|
| 76 |
PRIMARY KEY (gematria_sum, words, book, chapter, verse, word_position)
|
| 77 |
)
|
| 78 |
''')
|
|
|
|
| 94 |
# --- ELS Cache Functions ---
|
| 95 |
def create_els_cache_table():
|
| 96 |
with sqlite3.connect(ELS_CACHE_DB) as conn:
|
| 97 |
+
try:
|
| 98 |
+
conn.execute('''
|
| 99 |
+
CREATE TABLE IF NOT EXISTS els_cache (
|
| 100 |
+
query_hash TEXT PRIMARY KEY,
|
| 101 |
+
function_name TEXT,
|
| 102 |
+
args TEXT,
|
| 103 |
+
kwargs TEXT,
|
| 104 |
+
results TEXT
|
| 105 |
+
)
|
| 106 |
+
''')
|
| 107 |
+
except sqlite3.OperationalError as e:
|
| 108 |
+
logger.error(f"Error creating table: {e}")
|
| 109 |
+
|
| 110 |
+
def get_query_hash(func, args, kwargs):
|
| 111 |
+
key = (func.__name__, args, kwargs)
|
| 112 |
return hashlib.sha256(json.dumps(key).encode()).hexdigest()
|
| 113 |
|
| 114 |
|
| 115 |
def cached_process_json_files(func, *args, **kwargs):
|
| 116 |
+
# Create a dictionary to store the parameters
|
| 117 |
+
params = {
|
| 118 |
+
"function": f"{func.__module__}.{func.__name__}"
|
| 119 |
+
}
|
| 120 |
+
|
| 121 |
+
# Add the positional arguments with their names
|
| 122 |
+
arg_names = func.__code__.co_varnames[:func.__code__.co_argcount]
|
| 123 |
+
for name, value in zip(arg_names, args):
|
| 124 |
+
params[name] = value
|
| 125 |
+
|
| 126 |
+
# Add the keyword arguments
|
| 127 |
+
for name, value in kwargs.items():
|
| 128 |
+
params[name] = value
|
| 129 |
+
|
| 130 |
+
# Convert the parameters to a JSON string
|
| 131 |
+
params_json = json.dumps(params)
|
| 132 |
+
|
| 133 |
+
# Use the parameters JSON string to generate the query hash
|
| 134 |
+
query_hash = get_query_hash(func, params_json, "")
|
| 135 |
+
|
| 136 |
+
# Ensure the table exists before any operations
|
| 137 |
+
create_els_cache_table()
|
| 138 |
|
| 139 |
try:
|
| 140 |
with sqlite3.connect(ELS_CACHE_DB, timeout=DATABASE_TIMEOUT) as conn:
|
| 141 |
cursor = conn.cursor()
|
| 142 |
+
cursor.execute(
|
| 143 |
+
"SELECT results FROM els_cache WHERE query_hash = ?", (query_hash,))
|
| 144 |
result = cursor.fetchone()
|
| 145 |
if result:
|
| 146 |
logger.info(f"Cache hit for query: {query_hash}")
|
|
|
|
| 154 |
try:
|
| 155 |
with sqlite3.connect(ELS_CACHE_DB, timeout=DATABASE_TIMEOUT) as conn:
|
| 156 |
cursor = conn.cursor()
|
| 157 |
+
cursor.execute("INSERT INTO els_cache (query_hash, function_name, args, kwargs, results) VALUES (?, ?, ?, ?, ?)",
|
| 158 |
+
(query_hash, params["function"], params_json, json.dumps({}), json.dumps(results)))
|
| 159 |
conn.commit()
|
| 160 |
except sqlite3.Error as e:
|
| 161 |
logger.error(f"Database error caching results: {e}")
|
| 162 |
|
| 163 |
return results
|
| 164 |
|
| 165 |
+
|
| 166 |
# --- Helper Functions (from Network app.py) ---
|
| 167 |
def flatten_text(text: List) -> str:
|
| 168 |
if isinstance(text, list):
|
|
|
|
| 174 |
with sqlite3.connect(DATABASE_FILE) as conn:
|
| 175 |
cursor = conn.cursor()
|
| 176 |
cursor.execute('''
|
| 177 |
+
SELECT words, book, chapter, verse, phrase_length, word_position
|
| 178 |
+
FROM results
|
| 179 |
WHERE gematria_sum = ? AND phrase_length <= ?
|
| 180 |
''', (gematria_sum, max_words))
|
| 181 |
results = cursor.fetchall()
|
|
|
|
| 218 |
length = 0
|
| 219 |
|
| 220 |
selected_language_long = tlang # From the Gradio dropdown (long form)
|
| 221 |
+
# Get the short code.
|
| 222 |
+
tlang = LANGUAGES_SUPPORTED.get(selected_language_long)
|
| 223 |
+
if tlang is None: # Handle unsupported languages
|
| 224 |
tlang = "en"
|
| 225 |
+
logger.warning(
|
| 226 |
+
f"Unsupported language selected: {selected_language_long}. Defaulting to English (en).")
|
| 227 |
|
| 228 |
+
# Cache Update: Pass parameters individually
|
| 229 |
if include_torah:
|
| 230 |
+
logger.debug(
|
| 231 |
+
f"Arguments for Torah: {(1, 39, step, rounds_combination, length, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)}")
|
| 232 |
+
results["Torah"] = cached_process_json_files(torah.process_json_files, 1, 39, step, rounds_combination, length,
|
| 233 |
+
tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)
|
| 234 |
else:
|
| 235 |
results["Torah"] = []
|
| 236 |
|
| 237 |
if include_bible:
|
| 238 |
+
results["Bible"] = cached_process_json_files(bible.process_json_files, 40, 66, step, rounds_combination, length,
|
| 239 |
+
tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)
|
| 240 |
else:
|
| 241 |
results["Bible"] = []
|
| 242 |
|
| 243 |
if include_quran:
|
| 244 |
+
results["Quran"] = cached_process_json_files(quran.process_json_files, 1, 114, step, rounds_combination, length,
|
| 245 |
+
tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)
|
| 246 |
else:
|
| 247 |
results["Quran"] = []
|
| 248 |
|
| 249 |
if include_hindu:
|
| 250 |
+
results["Rig Veda"] = cached_process_json_files(
|
| 251 |
+
hindu.process_json_files, 1, 10, step, rounds_combination, length, tlang, False, strip_in_braces, strip_diacritics_chk)
|
| 252 |
else:
|
| 253 |
results["Rig Veda"] = []
|
| 254 |
|
| 255 |
if include_tripitaka:
|
| 256 |
+
results["Tripitaka"] = cached_process_json_files(
|
| 257 |
+
tripitaka.process_json_files, 1, 52, step, rounds_combination, length, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)
|
| 258 |
else:
|
| 259 |
results["Tripitaka"] = []
|
| 260 |
|
| 261 |
return results
|
| 262 |
|
| 263 |
|
| 264 |
+
|
| 265 |
def add_24h_projection(results_dict): #Now takes a dictionary of results
|
| 266 |
for book_name, results in results_dict.items(): # Iterate per book
|
| 267 |
num_results = len(results)
|
|
|
|
| 358 |
|
| 359 |
with gr.Row():
|
| 360 |
step = gr.Number(label="Jump Width (Steps) for ELS")
|
| 361 |
+
float_step = gr.Number(visible=False, value=1)
|
| 362 |
half_step_btn = gr.Button("Steps / 2")
|
| 363 |
double_step_btn = gr.Button("Steps * 2")
|
| 364 |
+
|
| 365 |
with gr.Column():
|
| 366 |
round_x = gr.Number(label="Round (1)", value=1)
|
| 367 |
round_y = gr.Number(label="Round (2)", value=-1)
|
| 368 |
+
|
| 369 |
rounds_combination = gr.Textbox(label="Combined Rounds", value="1,-1")
|
| 370 |
|
| 371 |
with gr.Row():
|
|
|
|
| 374 |
include_quran_chk = gr.Checkbox(label="Include Quran", value=True)
|
| 375 |
include_hindu_chk = gr.Checkbox(label="Include Rigveda", value=False)
|
| 376 |
include_tripitaka_chk = gr.Checkbox(label="Include Tripitaka", value=False)
|
| 377 |
+
|
| 378 |
strip_spaces = gr.Checkbox(label="Strip Spaces from Books", value=True)
|
| 379 |
strip_in_braces = gr.Checkbox(label="Strip Text in Braces from Books", value=True)
|
| 380 |
strip_diacritics_chk = gr.Checkbox(label="Strip Diacritics from Books", value=True)
|
els_cache.db
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:66db30b6eccaaaed442d806a1c1300f62238946ecc0bf09b77e9e385a4ad3458
|
| 3 |
-
size 12288
|
|
|
|
|
|
|
|
|
|
|
|
els_cache.db.initial
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:66db30b6eccaaaed442d806a1c1300f62238946ecc0bf09b77e9e385a4ad3458
|
| 3 |
-
size 12288
|
|
|
|
|
|
|
|
|
|
|
|