Spaces:
Running
Running
File size: 9,364 Bytes
9be760a 84b09e2 a8a8bc2 6c0aa26 9be760a 7445a27 e8bf2aa 9be760a 6c0aa26 940c3be 6c0aa26 84b09e2 6c0aa26 e8bf2aa 7b3be45 9be760a a13f26e 9be760a 84b09e2 a13f26e 9be760a e8bf2aa a13f26e e8bf2aa 84b09e2 a13f26e 84b09e2 a13f26e 6c0aa26 84b09e2 a13f26e 84b09e2 a13f26e 84b09e2 6c0aa26 a13f26e 6c0aa26 84b09e2 a13f26e 84b09e2 a13f26e 84b09e2 a13f26e 292d834 ce11247 42fc307 292d834 a13f26e 9be760a a13f26e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 |
import gradio as gr
import json
import re
import sqlite3
import logging
from collections import defaultdict
from util import process_json_files
from gematria import calculate_gematria
from deep_translator import GoogleTranslator, exceptions
from urllib.parse import quote_plus
# Set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
# Global variables for database connection and translator
conn = None
translator = None
book_names = {} # Dictionary to store book names
def flatten_text(text):
"""Helper function to flatten nested lists into a single list."""
if isinstance(text, list):
return " ".join(flatten_text(item) if isinstance(item, list) else item for item in text)
return text
def initialize_database():
"""Initializes the SQLite database."""
global conn
conn = sqlite3.connect('gematria.db')
c = conn.cursor()
c.execute('''
CREATE TABLE IF NOT EXISTS results (
gematria_sum INTEGER,
words TEXT,
translation TEXT,
book INTEGER,
chapter INTEGER,
verse INTEGER,
PRIMARY KEY (gematria_sum, book, chapter, verse)
)
''')
c.execute('''
CREATE TABLE IF NOT EXISTS processed_books (
book INTEGER PRIMARY KEY,
max_phrase_length INTEGER
)
''')
conn.commit()
logging.info("Database initialized.")
def initialize_translator():
"""Initializes the Google Translator."""
global translator
translator = GoogleTranslator(source='iw', target='en')
logging.info("Translator initialized.")
def insert_phrase_to_db(gematria_sum, phrase_candidate, book, chapter, verse):
"""Inserts a phrase and its Gematria value into the database."""
global conn
c = conn.cursor()
try:
c.execute('''
INSERT INTO results (gematria_sum, words, book, chapter, verse)
VALUES (?, ?, ?, ?, ?)
''', (gematria_sum, phrase_candidate, book, chapter, verse))
conn.commit()
logging.debug(f"Inserted phrase: {phrase_candidate} (Gematria: {gematria_sum}) at {book}:{chapter}:{verse}")
except sqlite3.IntegrityError:
logging.debug(f"Phrase already exists: {phrase_candidate} (Gematria: {gematria_sum}) at {book}:{chapter}:{verse}")
def populate_database(tanach_texts, max_phrase_length=1):
"""Populates the database with phrases from the Tanach and their Gematria values."""
global conn, book_names
logging.info("Populating database...")
c = conn.cursor()
for book_id, text in tanach_texts: # Unpack the tuple (book_id, text)
c.execute('''SELECT max_phrase_length FROM processed_books WHERE book = ?''', (book_id,))
result = c.fetchone()
if result and result[0] >= max_phrase_length:
logging.info(f"Skipping book {book_id}: Already processed with max_phrase_length {result[0]}")
continue
logging.info(f"Processing book {book_id} with max_phrase_length {max_phrase_length}")
if 'text' not in text or not isinstance(text['text'], list):
logging.warning(f"Skipping book {book_id} due to missing or invalid 'text' field.")
continue
title = text.get('title', 'Unknown')
book_names[book_id] = title # Store book name
chapters = text['text']
for chapter_id, chapter in enumerate(chapters):
if not isinstance(chapter, list):
logging.warning(f"Skipping chapter {chapter_id} in book {title} due to invalid format.")
continue
for verse_id, verse in enumerate(chapter):
verse_text = flatten_text(verse)
verse_text = re.sub(r"[^\u05D0-\u05EA ]+", "", verse_text)
verse_text = re.sub(r" +", " ", verse_text)
words = verse_text.split()
for length in range(1, max_phrase_length + 1):
for start in range(len(words) - length + 1):
phrase_candidate = " ".join(words[start:start + length])
gematria_sum = calculate_gematria(phrase_candidate.replace(" ", ""))
insert_phrase_to_db(gematria_sum, phrase_candidate, book_id, chapter_id + 1, verse_id + 1)
try:
c.execute('''INSERT INTO processed_books (book, max_phrase_length) VALUES (?, ?)''', (book_id, max_phrase_length))
except sqlite3.IntegrityError:
c.execute('''UPDATE processed_books SET max_phrase_length = ? WHERE book = ?''', (max_phrase_length, book_id))
conn.commit()
logging.info("Database population complete.")
def get_translation(phrase):
"""Retrieves or generates the English translation of a Hebrew phrase."""
global translator, conn
c = conn.cursor()
c.execute('''
SELECT translation FROM results
WHERE words = ?
''', (phrase,))
result = c.fetchone()
if result and result[0]:
return result[0]
else:
translation = translate_and_store(phrase)
c.execute('''
UPDATE results
SET translation = ?
WHERE words = ?
''', (translation, phrase))
conn.commit()
return translation
def translate_and_store(phrase):
global translator
max_retries = 3 # You can adjust the number of retries
retries = 0
while retries < max_retries:
try:
translation = translator.translate(phrase)
logging.debug(f"Translated phrase: {translation}")
return translation
except (exceptions.TranslationNotFound, exceptions.NotValidPayload,
exceptions.ServerException, exceptions.RequestError, requests.exceptions.ConnectionError) as e: # Add ConnectionError
retries += 1
logging.warning(f"Error translating phrase '{phrase}': {e}. Retrying... ({retries}/{max_retries})")
logging.error(f"Failed to translate phrase '{phrase}' after {max_retries} retries.")
return "[Translation Error]"
def search_gematria_in_db(gematria_sum):
"""Searches the database for phrases with a given Gematria value."""
global conn
c = conn.cursor()
c.execute('''
SELECT words, book, chapter, verse FROM results WHERE gematria_sum = ?
''', (gematria_sum,))
results = c.fetchall()
logging.debug(f"Found {len(results)} matching phrases for Gematria: {gematria_sum}")
return results
def gematria_search_interface(phrase):
"""The main function for the Gradio interface."""
if not phrase.strip():
return "Please enter a phrase."
# Create database connection inside the function
global conn, book_names
conn = sqlite3.connect('gematria.db')
c = conn.cursor()
phrase_gematria = calculate_gematria(phrase.replace(" ", ""))
logging.info(f"Searching for phrases with Gematria: {phrase_gematria}")
matching_phrases = search_gematria_in_db(phrase_gematria)
if not matching_phrases:
return "No matching phrases found."
# Sort results by book, chapter, and verse
sorted_phrases = sorted(matching_phrases, key=lambda x: (x[1], x[2], x[3]))
# Group results by book
results_by_book = defaultdict(list)
for words, book, chapter, verse in sorted_phrases:
results_by_book[book].append((words, chapter, verse))
# Format results for display with enhanced structure
results = []
results.append("<div class='results-container'>")
for book, phrases in results_by_book.items():
results.append(f"<h4>Book: {book_names.get(book, 'Unknown')}</h4>")
for words, chapter, verse in phrases:
translation = get_translation(words)
book_name_english = book_names.get(book, 'Unknown')
link = f"https://www.biblegateway.com/passage/?search={quote_plus(book_name_english)}+{chapter}%3A{verse}"
results.append(f"""
<div class='result-item'>
<p>Chapter: {chapter}, Verse: {verse}</p>
<p class='hebrew-phrase'>Hebrew Phrase: {words}</p>
<p>Translation: {translation}</p>
<a href='{link}' target='_blank' class='bible-link'>[See on Bible Gateway]</a>
</div>
""")
results.append("</div>") # Close results-container div
conn.close()
# Add CSS styling
style = """
<style>
.results-container {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(300px, 1fr));
gap: 20px;
}
.result-item {
border: 1px solid #ccc;
padding: 15px;
border-radius: 5px;
box-shadow: 2px 2px 5px rgba(0, 0, 0, 0.1);
}
.hebrew-phrase {
font-family: 'SBL Hebrew', 'Ezra SIL', serif;
direction: rtl;
}
.bible-link {
display: block;
margin-top: 10px;
color: #007bff;
text-decoration: none;
}
</style>
"""
return style + "\n".join(results) # Concatenate style and results
def run_app():
"""Initializes and launches the Gradio app."""
initialize_database()
initialize_translator()
# Pre-populate the database
tanach_texts = process_json_files(27, 27) # Process all books
populate_database(tanach_texts, max_phrase_length=12)
tanach_texts = process_json_files(1, 39) # Process all books
populate_database(tanach_texts, max_phrase_length=1)
#tanach_texts = process_json_files(1, 1) # Process all books
#populate_database(tanach_texts, max_phrase_length=4)
#tanach_texts = process_json_files(27, 27) # Process all books
#populate_database(tanach_texts, max_phrase_length=4)
iface = gr.Interface(
fn=gematria_search_interface,
inputs=gr.Textbox(label="Enter phrase"),
outputs=gr.HTML(label="Results"),
title="Gematria Search in Tanach",
description="Search for phrases in the Tanach that have the same Gematria value.",
live=False,
allow_flagging="never"
)
iface.launch()
if __name__ == "__main__":
run_app() |