Spaces:
Sleeping
Sleeping
Commit
·
2b9dfff
1
Parent(s):
e4ee4df
patch app.py
Browse files
app.py
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
import logging
|
2 |
-
|
3 |
logger = logging.getLogger(__name__)
|
4 |
logging.basicConfig(level=logging.DEBUG)
|
5 |
|
@@ -25,7 +24,6 @@ from typing import List, Tuple
|
|
25 |
DATABASE_FILE = 'gematria.db'
|
26 |
MAX_PHRASE_LENGTH_LIMIT = 20
|
27 |
|
28 |
-
|
29 |
# --- Database Initialization ---
|
30 |
def initialize_database():
|
31 |
global conn
|
@@ -40,7 +38,7 @@ def initialize_database():
|
|
40 |
chapter INTEGER,
|
41 |
verse INTEGER,
|
42 |
phrase_length INTEGER,
|
43 |
-
word_position TEXT,
|
44 |
PRIMARY KEY (gematria_sum, words, book, chapter, verse, word_position)
|
45 |
)
|
46 |
''')
|
@@ -56,31 +54,27 @@ def initialize_database():
|
|
56 |
''')
|
57 |
conn.commit()
|
58 |
|
59 |
-
|
60 |
# --- Initialize Database ---
|
61 |
initialize_database()
|
62 |
|
63 |
-
|
64 |
# --- Helper Functions (from Network app.py) ---
|
65 |
def flatten_text(text: List) -> str:
|
66 |
if isinstance(text, list):
|
67 |
return " ".join(flatten_text(item) if isinstance(item, list) else item for item in text)
|
68 |
return text
|
69 |
|
70 |
-
|
71 |
def search_gematria_in_db(gematria_sum: int, max_words: int) -> List[Tuple[str, str, int, int, int, str]]:
|
72 |
global conn
|
73 |
with sqlite3.connect(DATABASE_FILE) as conn:
|
74 |
cursor = conn.cursor()
|
75 |
cursor.execute('''
|
76 |
-
SELECT words, book, chapter, verse, phrase_length, word_position
|
77 |
-
FROM results
|
78 |
WHERE gematria_sum = ? AND phrase_length <= ?
|
79 |
''', (gematria_sum, max_words))
|
80 |
results = cursor.fetchall()
|
81 |
return results
|
82 |
|
83 |
-
|
84 |
def get_most_frequent_phrase(results):
|
85 |
phrase_counts = defaultdict(int)
|
86 |
for words, book, chapter, verse, phrase_length, word_position in results:
|
@@ -88,18 +82,16 @@ def get_most_frequent_phrase(results):
|
|
88 |
most_frequent_phrase = max(phrase_counts, key=phrase_counts.get) if phrase_counts else None # Handle empty results
|
89 |
return most_frequent_phrase
|
90 |
|
91 |
-
|
92 |
# --- Functions from BOS app.py ---
|
93 |
def create_language_dropdown(label, default_value='en', show_label=True):
|
94 |
languages = GoogleTranslator(source='en', target='en').get_supported_languages(as_dict=True)
|
95 |
return gr.Dropdown(
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
)
|
101 |
|
102 |
-
|
103 |
def calculate_gematria_sum(text, date_words):
|
104 |
if text or date_words:
|
105 |
combined_input = f"{text} {date_words}"
|
@@ -112,9 +104,7 @@ def calculate_gematria_sum(text, date_words):
|
|
112 |
else:
|
113 |
return None
|
114 |
|
115 |
-
|
116 |
-
def perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk,
|
117 |
-
merge_results, include_torah, include_bible, include_quran):
|
118 |
if step == 0 or rounds_combination == "0,0":
|
119 |
return None
|
120 |
|
@@ -123,19 +113,13 @@ def perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_b
|
|
123 |
quran_results = []
|
124 |
|
125 |
if include_torah:
|
126 |
-
torah_results.extend(
|
127 |
-
torah.process_json_files(1, 39, step, rounds_combination, 0, tlang, strip_spaces, strip_in_braces,
|
128 |
-
strip_diacritics))
|
129 |
|
130 |
if include_bible:
|
131 |
-
bible_results.extend(
|
132 |
-
bible.process_json_files(40, 66, step, rounds_combination, 0, tlang, strip_spaces, strip_in_braces,
|
133 |
-
strip_diacritics))
|
134 |
|
135 |
if include_quran:
|
136 |
-
quran_results.extend(
|
137 |
-
quran.process_json_files(1, 114, step, rounds_combination, 0, tlang, strip_spaces, strip_in_braces,
|
138 |
-
strip_diacritics))
|
139 |
|
140 |
if merge_results:
|
141 |
results = []
|
@@ -152,14 +136,12 @@ def perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_b
|
|
152 |
|
153 |
return results
|
154 |
|
155 |
-
|
156 |
-
|
157 |
-
search_phrase, results_df, start_date, end_date):
|
158 |
-
"""Generates the JSON dump with configuration, date range, and results."""
|
159 |
config = {
|
160 |
"Start Book": start,
|
161 |
"End Book": end,
|
162 |
-
"Step":
|
163 |
"Rounds": rounds_combination,
|
164 |
"Target Language": tlang,
|
165 |
"Strip Spaces": strip_spaces,
|
@@ -178,7 +160,6 @@ def generate_json_dump(start, end, step, rounds_combination, tlang, strip_spaces
|
|
178 |
logger.info(f"Generated JSON dump: {result}")
|
179 |
return json.dumps(result, indent=4, ensure_ascii=False)
|
180 |
|
181 |
-
|
182 |
def download_json_file(config_json, step, rounds_combination, strip_spaces, strip_in_braces, strip_diacritics_chk):
|
183 |
"""Downloads the JSON config file with a descriptive name."""
|
184 |
filename_suffix = ""
|
@@ -203,8 +184,7 @@ with gr.Blocks() as app:
|
|
203 |
|
204 |
with gr.Row():
|
205 |
tlang = create_language_dropdown("Target Language for Translation", default_value='english')
|
206 |
-
date_language_input = create_language_dropdown("Language of the person/topic (optional) (Date Word Language)",
|
207 |
-
default_value='english')
|
208 |
|
209 |
with gr.Row():
|
210 |
gematria_text = gr.Textbox(label="Name and/or Topic (required)", value="Hans Albert Einstein")
|
@@ -236,51 +216,45 @@ with gr.Blocks() as app:
|
|
236 |
|
237 |
# --- Output Components ---
|
238 |
markdown_output = gr.Dataframe(label="ELS Results")
|
239 |
-
most_frequent_phrase_output = gr.Textbox(label="Most Frequent Phrase in Network Search")
|
240 |
json_output = gr.Textbox(label="JSON Configuration Output")
|
241 |
json_download_btn = gr.Button("Prepare .json for Download")
|
242 |
json_file = gr.File(label="Download Config JSON", file_count="single")
|
243 |
|
244 |
-
|
245 |
# --- Event Handlers ---
|
246 |
def update_journal_sum(gematria_text, date_words_output):
|
247 |
sum_value = calculate_gematria_sum(gematria_text, date_words_output)
|
248 |
return sum_value, sum_value, sum_value
|
249 |
|
250 |
-
|
251 |
def update_rounds_combination(round_x, round_y):
|
252 |
return f"{int(round_x)},{int(round_y)}"
|
253 |
|
254 |
-
|
255 |
def update_step_half(float_step):
|
256 |
new_step = math.ceil(float_step / 2)
|
257 |
return new_step, float_step / 2
|
258 |
|
259 |
-
|
260 |
def update_step_double(float_step):
|
261 |
new_step = math.ceil(float_step * 2)
|
262 |
return new_step, float_step * 2
|
263 |
|
264 |
-
|
265 |
-
def perform_search(start_date, end_date, date_language_input, step, rounds_combination, tlang, strip_spaces,
|
266 |
-
strip_in_braces, strip_diacritics_chk, merge_results, include_torah, include_bible,
|
267 |
-
include_quran, gematria_text):
|
268 |
all_results = []
|
269 |
delta = timedelta(days=1)
|
270 |
current_date = start_date
|
271 |
|
|
|
|
|
272 |
while current_date <= end_date:
|
273 |
date_words_output = translate_date_to_words(current_date, date_language_input)
|
274 |
journal_sum, _, _ = update_journal_sum(gematria_text, date_words_output)
|
275 |
-
step = journal_sum
|
276 |
|
277 |
-
els_results = perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_braces,
|
278 |
-
strip_diacritics_chk, merge_results, include_torah, include_bible,
|
279 |
-
include_quran)
|
280 |
|
281 |
# --- Network Search Integration ---
|
282 |
updated_els_results = []
|
283 |
for result in els_results:
|
|
|
284 |
try:
|
285 |
gematria_sum = calculate_gematria(result['result_text'])
|
286 |
except KeyError as e:
|
@@ -301,8 +275,7 @@ with gr.Blocks() as app:
|
|
301 |
most_frequent_phrase = get_most_frequent_phrase(matching_phrases)
|
302 |
else:
|
303 |
# Sort initial results by word count and take the first phrase
|
304 |
-
sorted_results = sorted(search_gematria_in_db(gematria_sum, max_words_limit),
|
305 |
-
key=lambda x: len(x[0].split()))
|
306 |
most_frequent_phrase = sorted_results[0][0] if sorted_results else ""
|
307 |
|
308 |
# Add most frequent phrase, date, and date_words to the result dictionary
|
@@ -325,18 +298,14 @@ with gr.Blocks() as app:
|
|
325 |
most_frequent_phrase = max(set(all_phrases), key=all_phrases.count) if all_phrases else ""
|
326 |
|
327 |
# Generate JSON output
|
328 |
-
search_phrase = f"{gematria_text}"
|
329 |
-
config_json = generate_json_dump(1, 180,
|
330 |
-
strip_diacritics_chk, search_phrase, df, start_date, end_date)
|
331 |
-
|
332 |
-
return df, most_frequent_phrase, config_json
|
333 |
|
|
|
334 |
|
335 |
-
def handle_json_download(config_json, step, rounds_combination, strip_spaces, strip_in_braces,
|
336 |
-
strip_diacritics_chk):
|
337 |
"""Handles the download of the JSON config file."""
|
338 |
-
return download_json_file(config_json, step, rounds_combination, strip_spaces, strip_in_braces,
|
339 |
-
strip_diacritics_chk)
|
340 |
|
341 |
|
342 |
# --- Event Triggers ---
|
@@ -348,10 +317,8 @@ with gr.Blocks() as app:
|
|
348 |
|
349 |
translate_btn.click(
|
350 |
perform_search,
|
351 |
-
inputs=[start_date, end_date, date_language_input, step, rounds_combination, tlang, strip_spaces,
|
352 |
-
|
353 |
-
include_quran_chk, gematria_text],
|
354 |
-
outputs=[markdown_output, most_frequent_phrase_output, json_output]
|
355 |
)
|
356 |
|
357 |
json_download_btn.click(
|
@@ -361,4 +328,4 @@ with gr.Blocks() as app:
|
|
361 |
)
|
362 |
|
363 |
if __name__ == "__main__":
|
364 |
-
app.launch(share=False)
|
|
|
1 |
import logging
|
|
|
2 |
logger = logging.getLogger(__name__)
|
3 |
logging.basicConfig(level=logging.DEBUG)
|
4 |
|
|
|
24 |
DATABASE_FILE = 'gematria.db'
|
25 |
MAX_PHRASE_LENGTH_LIMIT = 20
|
26 |
|
|
|
27 |
# --- Database Initialization ---
|
28 |
def initialize_database():
|
29 |
global conn
|
|
|
38 |
chapter INTEGER,
|
39 |
verse INTEGER,
|
40 |
phrase_length INTEGER,
|
41 |
+
word_position TEXT,
|
42 |
PRIMARY KEY (gematria_sum, words, book, chapter, verse, word_position)
|
43 |
)
|
44 |
''')
|
|
|
54 |
''')
|
55 |
conn.commit()
|
56 |
|
|
|
57 |
# --- Initialize Database ---
|
58 |
initialize_database()
|
59 |
|
|
|
60 |
# --- Helper Functions (from Network app.py) ---
|
61 |
def flatten_text(text: List) -> str:
|
62 |
if isinstance(text, list):
|
63 |
return " ".join(flatten_text(item) if isinstance(item, list) else item for item in text)
|
64 |
return text
|
65 |
|
|
|
66 |
def search_gematria_in_db(gematria_sum: int, max_words: int) -> List[Tuple[str, str, int, int, int, str]]:
|
67 |
global conn
|
68 |
with sqlite3.connect(DATABASE_FILE) as conn:
|
69 |
cursor = conn.cursor()
|
70 |
cursor.execute('''
|
71 |
+
SELECT words, book, chapter, verse, phrase_length, word_position
|
72 |
+
FROM results
|
73 |
WHERE gematria_sum = ? AND phrase_length <= ?
|
74 |
''', (gematria_sum, max_words))
|
75 |
results = cursor.fetchall()
|
76 |
return results
|
77 |
|
|
|
78 |
def get_most_frequent_phrase(results):
|
79 |
phrase_counts = defaultdict(int)
|
80 |
for words, book, chapter, verse, phrase_length, word_position in results:
|
|
|
82 |
most_frequent_phrase = max(phrase_counts, key=phrase_counts.get) if phrase_counts else None # Handle empty results
|
83 |
return most_frequent_phrase
|
84 |
|
|
|
85 |
# --- Functions from BOS app.py ---
|
86 |
def create_language_dropdown(label, default_value='en', show_label=True):
|
87 |
languages = GoogleTranslator(source='en', target='en').get_supported_languages(as_dict=True)
|
88 |
return gr.Dropdown(
|
89 |
+
choices=list(languages.keys()),
|
90 |
+
label=label,
|
91 |
+
value=default_value,
|
92 |
+
show_label=show_label
|
93 |
)
|
94 |
|
|
|
95 |
def calculate_gematria_sum(text, date_words):
|
96 |
if text or date_words:
|
97 |
combined_input = f"{text} {date_words}"
|
|
|
104 |
else:
|
105 |
return None
|
106 |
|
107 |
+
def perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk, merge_results, include_torah, include_bible, include_quran):
|
|
|
|
|
108 |
if step == 0 or rounds_combination == "0,0":
|
109 |
return None
|
110 |
|
|
|
113 |
quran_results = []
|
114 |
|
115 |
if include_torah:
|
116 |
+
torah_results.extend(torah.process_json_files(1, 39, step, rounds_combination, 0, tlang, strip_spaces, strip_in_braces, strip_diacritics))
|
|
|
|
|
117 |
|
118 |
if include_bible:
|
119 |
+
bible_results.extend(bible.process_json_files(40, 66, step, rounds_combination, 0, tlang, strip_spaces, strip_in_braces, strip_diacritics))
|
|
|
|
|
120 |
|
121 |
if include_quran:
|
122 |
+
quran_results.extend(quran.process_json_files(1, 114, step, rounds_combination, 0, tlang, strip_spaces, strip_in_braces, strip_diacritics))
|
|
|
|
|
123 |
|
124 |
if merge_results:
|
125 |
results = []
|
|
|
136 |
|
137 |
return results
|
138 |
|
139 |
+
def generate_json_dump(start, end, initial_step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk, search_phrase, results_df, start_date, end_date):
|
140 |
+
"""Generates the JSON dump with configuration, date range, and results, including the initial step."""
|
|
|
|
|
141 |
config = {
|
142 |
"Start Book": start,
|
143 |
"End Book": end,
|
144 |
+
"Step": initial_step, # Use initial_step here
|
145 |
"Rounds": rounds_combination,
|
146 |
"Target Language": tlang,
|
147 |
"Strip Spaces": strip_spaces,
|
|
|
160 |
logger.info(f"Generated JSON dump: {result}")
|
161 |
return json.dumps(result, indent=4, ensure_ascii=False)
|
162 |
|
|
|
163 |
def download_json_file(config_json, step, rounds_combination, strip_spaces, strip_in_braces, strip_diacritics_chk):
|
164 |
"""Downloads the JSON config file with a descriptive name."""
|
165 |
filename_suffix = ""
|
|
|
184 |
|
185 |
with gr.Row():
|
186 |
tlang = create_language_dropdown("Target Language for Translation", default_value='english')
|
187 |
+
date_language_input = create_language_dropdown("Language of the person/topic (optional) (Date Word Language)", default_value='english')
|
|
|
188 |
|
189 |
with gr.Row():
|
190 |
gematria_text = gr.Textbox(label="Name and/or Topic (required)", value="Hans Albert Einstein")
|
|
|
216 |
|
217 |
# --- Output Components ---
|
218 |
markdown_output = gr.Dataframe(label="ELS Results")
|
219 |
+
#most_frequent_phrase_output = gr.Textbox(label="Most Frequent Phrase in Network Search")
|
220 |
json_output = gr.Textbox(label="JSON Configuration Output")
|
221 |
json_download_btn = gr.Button("Prepare .json for Download")
|
222 |
json_file = gr.File(label="Download Config JSON", file_count="single")
|
223 |
|
|
|
224 |
# --- Event Handlers ---
|
225 |
def update_journal_sum(gematria_text, date_words_output):
|
226 |
sum_value = calculate_gematria_sum(gematria_text, date_words_output)
|
227 |
return sum_value, sum_value, sum_value
|
228 |
|
|
|
229 |
def update_rounds_combination(round_x, round_y):
|
230 |
return f"{int(round_x)},{int(round_y)}"
|
231 |
|
|
|
232 |
def update_step_half(float_step):
|
233 |
new_step = math.ceil(float_step / 2)
|
234 |
return new_step, float_step / 2
|
235 |
|
|
|
236 |
def update_step_double(float_step):
|
237 |
new_step = math.ceil(float_step * 2)
|
238 |
return new_step, float_step * 2
|
239 |
|
240 |
+
def perform_search(start_date, end_date, date_language_input, step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk, merge_results, include_torah, include_bible, include_quran, gematria_text):
|
|
|
|
|
|
|
241 |
all_results = []
|
242 |
delta = timedelta(days=1)
|
243 |
current_date = start_date
|
244 |
|
245 |
+
initial_step = step # Store the initial step value
|
246 |
+
|
247 |
while current_date <= end_date:
|
248 |
date_words_output = translate_date_to_words(current_date, date_language_input)
|
249 |
journal_sum, _, _ = update_journal_sum(gematria_text, date_words_output)
|
250 |
+
step = journal_sum # Update step for each date
|
251 |
|
252 |
+
els_results = perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk, merge_results, include_torah, include_bible, include_quran)
|
|
|
|
|
253 |
|
254 |
# --- Network Search Integration ---
|
255 |
updated_els_results = []
|
256 |
for result in els_results:
|
257 |
+
logger.debug(f"Processing result: {result}") # Add debugging log
|
258 |
try:
|
259 |
gematria_sum = calculate_gematria(result['result_text'])
|
260 |
except KeyError as e:
|
|
|
275 |
most_frequent_phrase = get_most_frequent_phrase(matching_phrases)
|
276 |
else:
|
277 |
# Sort initial results by word count and take the first phrase
|
278 |
+
sorted_results = sorted(search_gematria_in_db(gematria_sum, max_words_limit), key=lambda x: len(x[0].split()))
|
|
|
279 |
most_frequent_phrase = sorted_results[0][0] if sorted_results else ""
|
280 |
|
281 |
# Add most frequent phrase, date, and date_words to the result dictionary
|
|
|
298 |
most_frequent_phrase = max(set(all_phrases), key=all_phrases.count) if all_phrases else ""
|
299 |
|
300 |
# Generate JSON output
|
301 |
+
search_phrase = f"{gematria_text}" # Removed date_words_output as it's now included in each result
|
302 |
+
config_json = generate_json_dump(1, 180, initial_step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk, search_phrase, df, start_date, end_date)
|
|
|
|
|
|
|
303 |
|
304 |
+
return df, config_json
|
305 |
|
306 |
+
def handle_json_download(config_json, step, rounds_combination, strip_spaces, strip_in_braces, strip_diacritics_chk):
|
|
|
307 |
"""Handles the download of the JSON config file."""
|
308 |
+
return download_json_file(config_json, step, rounds_combination, strip_spaces, strip_in_braces, strip_diacritics_chk)
|
|
|
309 |
|
310 |
|
311 |
# --- Event Triggers ---
|
|
|
317 |
|
318 |
translate_btn.click(
|
319 |
perform_search,
|
320 |
+
inputs=[start_date, end_date, date_language_input, step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk, merge_results_chk, include_torah_chk, include_bible_chk, include_quran_chk, gematria_text],
|
321 |
+
outputs=[markdown_output, json_output]
|
|
|
|
|
322 |
)
|
323 |
|
324 |
json_download_btn.click(
|
|
|
328 |
)
|
329 |
|
330 |
if __name__ == "__main__":
|
331 |
+
app.launch(share=False)
|