Spaces:
Sleeping
Sleeping
SSE for specifications
Browse files- app.py +30 -12
- classes.py +16 -2
- static/script.js +113 -21
app.py
CHANGED
|
@@ -74,7 +74,7 @@ def get_folder_name(working_group: str):
|
|
| 74 |
code, num = m.groups()
|
| 75 |
return (code, int(num))
|
| 76 |
else:
|
| 77 |
-
raise ValueError("
|
| 78 |
|
| 79 |
@app.get("/get_meetings/{working_group}")
|
| 80 |
def get_meetings(working_group: str):
|
|
@@ -98,7 +98,7 @@ def index_tdocs_wg_progress(req: IndexTDoc):
|
|
| 98 |
for content in tdoc_indexer.process_workgroup(folder, url):
|
| 99 |
yield content
|
| 100 |
tdoc_indexer.save_indexer()
|
| 101 |
-
yield "event: end\ndata: Indexation
|
| 102 |
return StreamingResponse(generate_events(), media_type="text/event-stream")
|
| 103 |
|
| 104 |
@app.post("/index_tdocs/meeting")
|
|
@@ -118,7 +118,7 @@ def index_tdocs_meeting_progress(req: IndexTDoc):
|
|
| 118 |
tdoc_indexer.process_meeting(meet, url)
|
| 119 |
yield f"event: progress\ndata: {i+1}\n\n"
|
| 120 |
tdoc_indexer.save_indexer()
|
| 121 |
-
yield "event: end\ndata: Indexation
|
| 122 |
return StreamingResponse(generate_events(), media_type="text/event-stream")
|
| 123 |
|
| 124 |
|
|
@@ -128,20 +128,38 @@ def index_all_tdocs_progress():
|
|
| 128 |
for content in tdoc_indexer.index_all_tdocs():
|
| 129 |
yield content
|
| 130 |
tdoc_indexer.save_indexer()
|
| 131 |
-
yield "event: end\ndata: Indexation
|
| 132 |
return StreamingResponse(generate_events(), media_type="text/event-stream")
|
| 133 |
|
| 134 |
|
| 135 |
@app.post("/index_specs/3gpp")
|
| 136 |
def index_3gpp_specs_progress():
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
|
| 142 |
@app.post("/index_specs/etsi")
|
| 143 |
def index_etsi_specs_progress():
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
code, num = m.groups()
|
| 75 |
return (code, int(num))
|
| 76 |
else:
|
| 77 |
+
raise ValueError("Unattended format")
|
| 78 |
|
| 79 |
@app.get("/get_meetings/{working_group}")
|
| 80 |
def get_meetings(working_group: str):
|
|
|
|
| 98 |
for content in tdoc_indexer.process_workgroup(folder, url):
|
| 99 |
yield content
|
| 100 |
tdoc_indexer.save_indexer()
|
| 101 |
+
yield "event: end\ndata: Indexation ended successfully !\n\n"
|
| 102 |
return StreamingResponse(generate_events(), media_type="text/event-stream")
|
| 103 |
|
| 104 |
@app.post("/index_tdocs/meeting")
|
|
|
|
| 118 |
tdoc_indexer.process_meeting(meet, url)
|
| 119 |
yield f"event: progress\ndata: {i+1}\n\n"
|
| 120 |
tdoc_indexer.save_indexer()
|
| 121 |
+
yield "event: end\ndata: Indexation ended successfully !\n\n"
|
| 122 |
return StreamingResponse(generate_events(), media_type="text/event-stream")
|
| 123 |
|
| 124 |
|
|
|
|
| 128 |
for content in tdoc_indexer.index_all_tdocs():
|
| 129 |
yield content
|
| 130 |
tdoc_indexer.save_indexer()
|
| 131 |
+
yield "event: end\ndata: Indexation ended successfully !\n\n"
|
| 132 |
return StreamingResponse(generate_events(), media_type="text/event-stream")
|
| 133 |
|
| 134 |
|
| 135 |
@app.post("/index_specs/3gpp")
|
| 136 |
def index_3gpp_specs_progress():
|
| 137 |
+
def generate_events():
|
| 138 |
+
for content in spec_3gpp_indexer.run():
|
| 139 |
+
yield content
|
| 140 |
+
yield "event: info\ndata: Saving index ...\n\n"
|
| 141 |
+
yield "event: get-maximum\ndata: 1\n\n"
|
| 142 |
+
yield "event: progress\ndata: 1\n\n"
|
| 143 |
+
spec_3gpp_indexer.save()
|
| 144 |
+
yield "event: info\ndata: Creating BM25 models ...\n\n"
|
| 145 |
+
yield "event: get-maximum\ndata: 1\n\n"
|
| 146 |
+
yield "event: progress\ndata: 1\n\n"
|
| 147 |
+
spec_3gpp_indexer.create_bm25_index()
|
| 148 |
+
yield "event: end\ndata: Indexation ended successfully !\n\n"
|
| 149 |
+
return StreamingResponse(generate_events(), media_type="text/event-stream")
|
| 150 |
|
| 151 |
@app.post("/index_specs/etsi")
|
| 152 |
def index_etsi_specs_progress():
|
| 153 |
+
def generate_events():
|
| 154 |
+
for content in spec_etsi_indexer.run():
|
| 155 |
+
yield content
|
| 156 |
+
yield "event: info\ndata: Saving index ...\n\n"
|
| 157 |
+
yield "event: get-maximum\ndata: 1\n\n"
|
| 158 |
+
yield "event: progress\ndata: 1\n\n"
|
| 159 |
+
spec_etsi_indexer.save()
|
| 160 |
+
yield "event: info\ndata: Creating BM25 models ...\n\n"
|
| 161 |
+
yield "event: get-maximum\ndata: 1\n\n"
|
| 162 |
+
yield "event: progress\ndata: 1\n\n"
|
| 163 |
+
spec_etsi_indexer.create_bm25_index()
|
| 164 |
+
yield "event: end\ndata: Indexation ended successfully !\n\n"
|
| 165 |
+
return StreamingResponse(generate_events(), media_type="text/event-stream")
|
classes.py
CHANGED
|
@@ -538,12 +538,19 @@ class Spec3GPPIndexer:
|
|
| 538 |
|
| 539 |
def run(self):
|
| 540 |
print("Fetching specification tables from 3GPP...")
|
|
|
|
| 541 |
specifications = self.fetch_spec_table()
|
| 542 |
self.total_count = len(specifications)
|
| 543 |
print(f"Processing {self.total_count} specs with {self.max_workers} threads...")
|
| 544 |
with concurrent.futures.ThreadPoolExecutor(max_workers=self.max_workers) as executor:
|
| 545 |
futures = [executor.submit(self.process_specification, spec) for spec in specifications]
|
| 546 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 547 |
if self.STOP_EVENT.is_set():
|
| 548 |
break
|
| 549 |
print("All specs processed.")
|
|
@@ -776,13 +783,20 @@ class SpecETSIIndexer:
|
|
| 776 |
|
| 777 |
def run(self):
|
| 778 |
print("Démarrage indexation ETSI…")
|
|
|
|
| 779 |
specifications = self.df.to_dict(orient="records")
|
| 780 |
self.total_count = len(specifications)
|
| 781 |
print(f"Traitement de {self.total_count} specs avec {self.max_workers} threads...\n")
|
| 782 |
|
| 783 |
with concurrent.futures.ThreadPoolExecutor(max_workers=self.max_workers) as executor:
|
| 784 |
futures = [executor.submit(self.process_specification, spec) for spec in specifications]
|
| 785 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 786 |
if self.STOP_EVENT.is_set():
|
| 787 |
break
|
| 788 |
|
|
|
|
| 538 |
|
| 539 |
def run(self):
|
| 540 |
print("Fetching specification tables from 3GPP...")
|
| 541 |
+
yield "event: info\ndata: Indexing 3GPP specs ...\n\n"
|
| 542 |
specifications = self.fetch_spec_table()
|
| 543 |
self.total_count = len(specifications)
|
| 544 |
print(f"Processing {self.total_count} specs with {self.max_workers} threads...")
|
| 545 |
with concurrent.futures.ThreadPoolExecutor(max_workers=self.max_workers) as executor:
|
| 546 |
futures = [executor.submit(self.process_specification, spec) for spec in specifications]
|
| 547 |
+
total = len(futures)
|
| 548 |
+
done_count = 0
|
| 549 |
+
yield f"event: get-maximum\ndata: {total}\n\n"
|
| 550 |
+
|
| 551 |
+
for future in concurrent.futures.as_completed(futures):
|
| 552 |
+
done_count += 1
|
| 553 |
+
yield f"event: progress\ndata: {done_count}\n\n"
|
| 554 |
if self.STOP_EVENT.is_set():
|
| 555 |
break
|
| 556 |
print("All specs processed.")
|
|
|
|
| 783 |
|
| 784 |
def run(self):
|
| 785 |
print("Démarrage indexation ETSI…")
|
| 786 |
+
yield "event: info\ndata: Indexing ETSI specs ...\n\n"
|
| 787 |
specifications = self.df.to_dict(orient="records")
|
| 788 |
self.total_count = len(specifications)
|
| 789 |
print(f"Traitement de {self.total_count} specs avec {self.max_workers} threads...\n")
|
| 790 |
|
| 791 |
with concurrent.futures.ThreadPoolExecutor(max_workers=self.max_workers) as executor:
|
| 792 |
futures = [executor.submit(self.process_specification, spec) for spec in specifications]
|
| 793 |
+
total = len(futures)
|
| 794 |
+
done_count = 0
|
| 795 |
+
yield f"event: get-maximum\ndata: {total}\n\n"
|
| 796 |
+
|
| 797 |
+
for future in concurrent.futures.as_completed(futures):
|
| 798 |
+
done_count += 1
|
| 799 |
+
yield f"event: progress\ndata: {done_count}\n\n"
|
| 800 |
if self.STOP_EVENT.is_set():
|
| 801 |
break
|
| 802 |
|
static/script.js
CHANGED
|
@@ -198,7 +198,7 @@ document.getElementById('tdocs-btn').addEventListener('click', async () => {
|
|
| 198 |
break;
|
| 199 |
case "end":
|
| 200 |
console.log("[end]", event.data);
|
| 201 |
-
document.getElementById('infoText').textContent =
|
| 202 |
break;
|
| 203 |
default:
|
| 204 |
if (event.data) {
|
|
@@ -211,30 +211,122 @@ document.getElementById('tdocs-btn').addEventListener('click', async () => {
|
|
| 211 |
enableButtons()
|
| 212 |
});
|
| 213 |
|
| 214 |
-
document.getElementById('spec-3gpp-btn').addEventListener('click', () => {
|
| 215 |
disableButtons()
|
| 216 |
-
fetch("/index_specs/3gpp", {
|
| 217 |
-
|
| 218 |
-
|
| 219 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
}
|
| 221 |
-
}
|
| 222 |
-
|
| 223 |
-
|
| 224 |
-
|
| 225 |
-
})
|
| 226 |
});
|
| 227 |
|
| 228 |
-
document.getElementById('spec-etsi-btn').addEventListener('click', () => {
|
| 229 |
disableButtons()
|
| 230 |
-
fetch("/index_specs/etsi", {
|
| 231 |
-
|
| 232 |
-
|
| 233 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 234 |
}
|
| 235 |
-
}
|
| 236 |
-
|
| 237 |
-
|
| 238 |
-
|
| 239 |
-
})
|
| 240 |
});
|
|
|
|
| 198 |
break;
|
| 199 |
case "end":
|
| 200 |
console.log("[end]", event.data);
|
| 201 |
+
document.getElementById('infoText').textContent = event.data;
|
| 202 |
break;
|
| 203 |
default:
|
| 204 |
if (event.data) {
|
|
|
|
| 211 |
enableButtons()
|
| 212 |
});
|
| 213 |
|
| 214 |
+
document.getElementById('spec-3gpp-btn').addEventListener('click', async () => {
|
| 215 |
disableButtons()
|
| 216 |
+
const response = await fetch("/index_specs/3gpp", {method: "POST", headers: {
|
| 217 |
+
"Content-Type": "application/json",
|
| 218 |
+
"Accept": "text/event-stream",
|
| 219 |
+
}});
|
| 220 |
+
const reader = response.body.getReader();
|
| 221 |
+
const decoder = new TextDecoder("utf-8");
|
| 222 |
+
let buffer = "";
|
| 223 |
+
|
| 224 |
+
while (true) {
|
| 225 |
+
const {
|
| 226 |
+
done,
|
| 227 |
+
value
|
| 228 |
+
} = await reader.read();
|
| 229 |
+
if (done) break;
|
| 230 |
+
|
| 231 |
+
buffer += decoder.decode(value, {
|
| 232 |
+
stream: true
|
| 233 |
+
});
|
| 234 |
+
|
| 235 |
+
let events = buffer.split("\n\n"); // séparer les événements
|
| 236 |
+
buffer = events.pop(); // garder le reste pour le prochain chunk
|
| 237 |
+
|
| 238 |
+
for (const rawEvent of events) {
|
| 239 |
+
const event = {};
|
| 240 |
+
rawEvent.split("\n").forEach((line) => {
|
| 241 |
+
const [key, ...rest] = line.split(":");
|
| 242 |
+
if (key) event[key.trim()] = rest.join(":").trim();
|
| 243 |
+
});
|
| 244 |
+
|
| 245 |
+
// dispatch selon event.event ou par défaut message
|
| 246 |
+
switch (event.event) {
|
| 247 |
+
case "progress":
|
| 248 |
+
console.log("[progress]", event.data);
|
| 249 |
+
progress.value = event.data;
|
| 250 |
+
break;
|
| 251 |
+
case "get-maximum":
|
| 252 |
+
console.log("[new-max]", event.data);
|
| 253 |
+
progress.max = event.data
|
| 254 |
+
break;
|
| 255 |
+
case "info":
|
| 256 |
+
console.log("[info]", event.data);
|
| 257 |
+
document.getElementById('infoText').textContent = event.data
|
| 258 |
+
break;
|
| 259 |
+
case "end":
|
| 260 |
+
console.log("[end]", event.data);
|
| 261 |
+
document.getElementById('infoText').textContent = event.data;
|
| 262 |
+
break;
|
| 263 |
+
default:
|
| 264 |
+
if (event.data) {
|
| 265 |
+
console.log("[message]", event.data);
|
| 266 |
+
};
|
| 267 |
}
|
| 268 |
+
}
|
| 269 |
+
}
|
| 270 |
+
|
| 271 |
+
enableButtons()
|
|
|
|
| 272 |
});
|
| 273 |
|
| 274 |
+
document.getElementById('spec-etsi-btn').addEventListener('click', async () => {
|
| 275 |
disableButtons()
|
| 276 |
+
const response = await fetch("/index_specs/etsi", {method: "POST", headers: {
|
| 277 |
+
"Content-Type": "application/json",
|
| 278 |
+
"Accept": "text/event-stream",
|
| 279 |
+
}});
|
| 280 |
+
const reader = response.body.getReader();
|
| 281 |
+
const decoder = new TextDecoder("utf-8");
|
| 282 |
+
let buffer = "";
|
| 283 |
+
|
| 284 |
+
while (true) {
|
| 285 |
+
const {
|
| 286 |
+
done,
|
| 287 |
+
value
|
| 288 |
+
} = await reader.read();
|
| 289 |
+
if (done) break;
|
| 290 |
+
|
| 291 |
+
buffer += decoder.decode(value, {
|
| 292 |
+
stream: true
|
| 293 |
+
});
|
| 294 |
+
|
| 295 |
+
let events = buffer.split("\n\n"); // séparer les événements
|
| 296 |
+
buffer = events.pop(); // garder le reste pour le prochain chunk
|
| 297 |
+
|
| 298 |
+
for (const rawEvent of events) {
|
| 299 |
+
const event = {};
|
| 300 |
+
rawEvent.split("\n").forEach((line) => {
|
| 301 |
+
const [key, ...rest] = line.split(":");
|
| 302 |
+
if (key) event[key.trim()] = rest.join(":").trim();
|
| 303 |
+
});
|
| 304 |
+
|
| 305 |
+
// dispatch selon event.event ou par défaut message
|
| 306 |
+
switch (event.event) {
|
| 307 |
+
case "progress":
|
| 308 |
+
console.log("[progress]", event.data);
|
| 309 |
+
progress.value = event.data;
|
| 310 |
+
break;
|
| 311 |
+
case "get-maximum":
|
| 312 |
+
console.log("[new-max]", event.data);
|
| 313 |
+
progress.max = event.data
|
| 314 |
+
break;
|
| 315 |
+
case "info":
|
| 316 |
+
console.log("[info]", event.data);
|
| 317 |
+
document.getElementById('infoText').textContent = event.data
|
| 318 |
+
break;
|
| 319 |
+
case "end":
|
| 320 |
+
console.log("[end]", event.data);
|
| 321 |
+
document.getElementById('infoText').textContent = event.data;
|
| 322 |
+
break;
|
| 323 |
+
default:
|
| 324 |
+
if (event.data) {
|
| 325 |
+
console.log("[message]", event.data);
|
| 326 |
+
};
|
| 327 |
}
|
| 328 |
+
}
|
| 329 |
+
}
|
| 330 |
+
|
| 331 |
+
enableButtons()
|
|
|
|
| 332 |
});
|