Repository navigation
Expand file tree
/
Copy pathcli_helpers.py
More file actions
1179 lines (981 loc) · 39.8 KB
/
Copy pathcli_helpers.py
File metadata and controls
1179 lines (981 loc) · 39.8 KB
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
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import asyncio
import json
import traceback
import uuid
import urllib.parse
import threading
from pathlib import Path
import time
from typing import Optional
from rich.console import Console
from rich.table import Table
from rich.progress import (
Progress,
SpinnerColumn,
TextColumn,
BarColumn,
TaskProgressColumn,
TimeRemainingColumn,
MofNCompleteColumn,
)
from ..core import get_database_manager
from ..core.jobs import JobManager
from ..tools.code_finder import CodeFinder
from ..tools.graph_builder import GraphBuilder
from ..tools.package_resolver import get_local_package_path
from ..utils.debug_log import error_logger
console = Console()
def _iter_exception_chain(exc: Exception) -> list[Exception]:
chain: list[Exception] = []
seen: set[int] = set()
current: Optional[BaseException] = exc
while current is not None and id(current) not in seen:
seen.add(id(current))
if isinstance(current, Exception):
chain.append(current)
next_exc = current.__cause__
if next_exc is None and not getattr(current, "__suppress_context__", False):
next_exc = current.__context__
current = next_exc
return chain
def _format_cli_exception(exc: Exception) -> str:
chain = _iter_exception_chain(exc)
chain_parts = [f"{type(item).__name__}: {item}" for item in chain if str(item)]
if not chain_parts:
chain_parts = [type(exc).__name__]
details = [f"Cause chain: {' -> '.join(chain_parts)}"]
deepest = chain[-1] if chain else exc
extracted = (
traceback.extract_tb(deepest.__traceback__) if deepest.__traceback__ else []
)
if extracted:
frame = extracted[-1]
details.append(
f"Traceback location: {Path(frame.filename).name}:{frame.lineno} in {frame.name}"
)
if frame.line:
details.append(f"Failing line: {frame.line.strip()}")
return "\n".join(details)
def _print_cli_exception(prefix: str, exc: Exception) -> None:
console.print(f"[bold red]{prefix}[/bold red] {exc}")
console.print(f"[red]{_format_cli_exception(exc)}[/red]")
error_logger(traceback.format_exc())
def _format_job_failure(job) -> str:
summary = job.errors[0] if job.errors else "Unknown error"
details = [summary]
if job.error_type:
details.append(f"Error type: {job.error_type}")
if job.current_phase:
details.append(f"Job phase: {job.current_phase}")
if job.current_file:
details.append(f"Current item: {job.current_file}")
if job.error_details:
details.append("Original traceback:")
details.append(job.error_details.rstrip())
return "\n".join(details)
def _initialize_services():
"""Initializes and returns core service managers."""
console.print("[dim]Initializing services and database connection...[/dim]")
try:
db_manager = get_database_manager()
except ValueError as e:
console.print(f"[bold red]Database Configuration Error:[/bold red] {e}")
return None, None, None
try:
db_manager.get_driver()
except Exception as e:
# Check if this is a FalkorDB failure that should trigger a KùzuDB fallback
from ..core.database_falkordb import FalkorDBUnavailableError
if isinstance(e, FalkorDBUnavailableError):
console.print(
f"[yellow]⚠ FalkorDB Lite is not functional in this environment: {e}[/yellow]"
)
console.print(
"[cyan]Falling back to KùzuDB for a reliable experience...[/cyan]"
)
# Close the broken driver/socket
try:
db_manager.close_driver()
except Exception:
pass
# Re-initialize explicitly with KùzuDB
from ..core.database_kuzu import KuzuDBManager
db_manager = KuzuDBManager()
try:
db_manager.get_driver()
console.print(
"[green]✓[/green] Successfully switched to KùzuDB fallback"
)
except Exception as kuzu_e:
console.print(
f"[bold red]Critical Error:[/bold red] Both FalkorDB and KùzuDB failed: {kuzu_e}"
)
return None, None, None
else:
console.print(f"[bold red]Database Connection Error:[/bold red] {e}")
console.print(
"Please ensure your database is configured correctly or run 'cgc doctor'."
)
return None, None, None
# The GraphBuilder requires an event loop, even for synchronous-style execution
try:
loop = asyncio.get_running_loop()
except RuntimeError:
loop = asyncio.new_event_loop()
asyncio.set_event_loop(loop)
graph_builder = GraphBuilder(db_manager, JobManager(), loop)
code_finder = CodeFinder(db_manager)
console.print("[dim]Services initialized.[/dim]")
return db_manager, graph_builder, code_finder
async def _run_index_with_progress(
graph_builder: GraphBuilder, path_obj: Path, is_dependency: bool = False
):
"""Internal helper to run indexing with a Live progress bar."""
job_id = graph_builder.job_manager.create_job(
str(path_obj), is_dependency=is_dependency
)
with Progress(
SpinnerColumn(),
TextColumn("[progress.description]{task.description}"),
BarColumn(),
TaskProgressColumn(),
MofNCompleteColumn(),
TimeRemainingColumn(),
TextColumn("[dim]{task.fields[filename]}"),
TextColumn("[cyan]{task.fields[detail]}"),
console=console,
auto_refresh=False,
transient=True,
) as progress:
task_id = progress.add_task(
"Indexing...",
total=None,
filename="",
detail="",
)
thread_result: dict[str, object] = {}
def run_indexing_job() -> None:
try:
asyncio.run(
graph_builder.build_graph_from_path_async(
path_obj,
is_dependency=is_dependency,
job_id=job_id,
)
)
except Exception as exc:
thread_result["exception"] = exc
indexing_thread = threading.Thread(
target=run_indexing_job,
name=f"cgc-index-{job_id[:8]}",
daemon=True,
)
indexing_thread.start()
from ..core.jobs import JobStatus
last_snapshot = None
while indexing_thread.is_alive():
job = graph_builder.job_manager.get_job(job_id)
if job:
phase = job.current_phase or "indexing"
current_file = job.current_file or ""
if len(current_file) > 40:
current_file = "..." + current_file[-37:]
detail = job.progress_detail or ""
if len(detail) > 60:
detail = detail[:57] + "..."
snapshot = (
phase,
job.total_files,
job.processed_files,
current_file,
detail,
job.status,
)
if snapshot != last_snapshot:
update_kwargs = {
"description": f"{phase.replace('_', ' ').title()}...",
"filename": current_file,
"detail": detail,
}
if job.total_files > 0:
update_kwargs["total"] = job.total_files
update_kwargs["completed"] = job.processed_files
progress.update(task_id, **update_kwargs)
progress.refresh()
last_snapshot = snapshot
if job.status in [
JobStatus.COMPLETED,
JobStatus.FAILED,
JobStatus.CANCELLED,
]:
break
await asyncio.sleep(0.1)
indexing_thread.join()
if "exception" in thread_result:
raise thread_result["exception"]
job = graph_builder.job_manager.get_job(job_id)
if job and job.status == JobStatus.FAILED:
raise RuntimeError(_format_job_failure(job))
def index_helper(path: str):
"""Synchronously indexes a repository."""
time_start = time.time()
services = _initialize_services()
if not all(services):
return
db_manager, graph_builder, code_finder = services
path_obj = Path(path).resolve()
if not path_obj.exists():
console.print(f"[red]Error: Path does not exist: {path_obj}[/red]")
db_manager.close_driver()
return
indexed_repos = code_finder.list_indexed_repositories()
repo_exists = any(
Path(repo["path"]).resolve() == path_obj for repo in indexed_repos
)
if repo_exists:
# Check if the repository actually has files (not just an empty node from interrupted indexing)
try:
with db_manager.get_driver().session() as session:
result = session.run(
"MATCH (r:Repository {path: $path})-[:CONTAINS]->(f:File) RETURN count(f) as file_count",
path=str(path_obj),
)
record = result.single()
file_count = record["file_count"] if record else 0
if file_count > 0:
console.print(
f"[yellow]Repository '{path}' is already indexed with {file_count} files. Skipping.[/yellow]"
)
console.print(
"[dim]💡 Tip: Use 'cgc index --force' to re-index[/dim]"
)
db_manager.close_driver()
return
else:
console.print(
f"[yellow]Repository '{path}' exists but has no files (likely interrupted). Re-indexing...[/yellow]"
)
except Exception as e:
console.print(
f"[yellow]Warning: Could not check file count: {e}. Proceeding with indexing...[/yellow]"
)
console.print(f"Starting indexing for: {path_obj}")
try:
asyncio.run(
_run_index_with_progress(graph_builder, path_obj, is_dependency=False)
)
time_end = time.time()
elapsed = time_end - time_start
console.print(
f"[green]Successfully finished indexing: {path} in {elapsed:.2f} seconds[/green]"
)
# Check if auto-watch is enabled
try:
from codegraphcontext.cli.config_manager import get_config_value
auto_watch = get_config_value("ENABLE_AUTO_WATCH")
if auto_watch and str(auto_watch).lower() == "true":
console.print(
"\n[cyan]🔍 ENABLE_AUTO_WATCH is enabled. Starting watcher...[/cyan]"
)
db_manager.close_driver() # Close before starting watcher
watch_helper(path) # This will block the terminal
return # watch_helper handles its own cleanup
except Exception as e:
console.print(
f"[yellow]Warning: Could not check ENABLE_AUTO_WATCH: {e}[/yellow]"
)
except Exception as e:
_print_cli_exception("An error occurred during indexing:", e)
finally:
db_manager.close_driver()
def add_package_helper(package_name: str, language: str):
"""Synchronously indexes a package."""
services = _initialize_services()
if not all(services):
return
db_manager, graph_builder, code_finder = services
package_path_str = get_local_package_path(package_name, language)
if not package_path_str:
console.print(
f"[red]Error: Could not find package '{package_name}' for language '{language}'.[/red]"
)
db_manager.close_driver()
return
package_path = Path(package_path_str)
indexed_repos = code_finder.list_indexed_repositories()
if any(
repo.get("name") == package_name
for repo in indexed_repos
if repo.get("is_dependency")
):
console.print(
f"[yellow]Package '{package_name}' is already indexed. Skipping.[/yellow]"
)
db_manager.close_driver()
return
console.print(f"Starting indexing for package '{package_name}' at: {package_path}")
try:
asyncio.run(
_run_index_with_progress(graph_builder, package_path, is_dependency=True)
)
console.print(
f"[green]Successfully finished indexing package: {package_name}[/green]"
)
except Exception as e:
console.print(
f"[bold red]An error occurred during package indexing:[/bold red] {e}"
)
finally:
db_manager.close_driver()
def list_repos_helper():
"""Lists all indexed repositories."""
services = _initialize_services()
if not all(services):
return
db_manager, _, code_finder = services
try:
repos = code_finder.list_indexed_repositories()
if not repos:
console.print("[yellow]No repositories indexed yet.[/yellow]")
return
table = Table(show_header=True, header_style="bold magenta")
table.add_column("Name", style="dim")
table.add_column("Path")
table.add_column("Type")
for repo in repos:
repo_type = "Dependency" if repo.get("is_dependency") else "Project"
table.add_row(repo["name"], repo["path"], repo_type)
console.print(table)
except Exception as e:
console.print(f"[bold red]An error occurred:[/bold red] {e}")
finally:
db_manager.close_driver()
def delete_helper(repo_path: str):
"""Deletes a repository from the graph."""
services = _initialize_services()
if not all(services):
return
db_manager, graph_builder, _ = services
try:
if graph_builder.delete_repository_from_graph(repo_path):
console.print(
f"[green]Successfully deleted repository: {repo_path}[/green]"
)
else:
console.print(
f"[yellow]Repository not found in graph: {repo_path}[/yellow]"
)
console.print(
"[dim]Tip: Use 'cgc list' to see available repositories.[/dim]"
)
except Exception as e:
console.print(f"[bold red]An error occurred:[/bold red] {e}")
finally:
db_manager.close_driver()
def cypher_helper(query: str):
"""Executes a read-only Cypher query."""
services = _initialize_services()
if not all(services):
return
db_manager, _, _ = services
# Replicating safety checks from MCPServer
forbidden_keywords = [
"CREATE",
"MERGE",
"DELETE",
"SET",
"REMOVE",
"DROP",
"CALL apoc",
]
if any(keyword in query.upper() for keyword in forbidden_keywords):
console.print(
"[bold red]Error: This command only supports read-only queries.[/bold red]"
)
db_manager.close_driver()
return
try:
with db_manager.get_driver().session() as session:
result = session.run(query)
records = [record.data() for record in result]
console.print(json.dumps(records, indent=2))
except Exception as e:
console.print(
f"[bold red]An error occurred while executing query:[/bold red] {e}"
)
finally:
db_manager.close_driver()
def cypher_helper_visual(query: str):
"""Executes a read-only Cypher query and visualizes the results."""
from .visualizer import visualize_cypher_results
services = _initialize_services()
if not all(services):
return
db_manager, _, _ = services
# Replicating safety checks from MCPServer
forbidden_keywords = [
"CREATE",
"MERGE",
"DELETE",
"SET",
"REMOVE",
"DROP",
"CALL apoc",
]
if any(keyword in query.upper() for keyword in forbidden_keywords):
console.print(
"[bold red]Error: This command only supports read-only queries.[/bold red]"
)
db_manager.close_driver()
return
try:
with db_manager.get_driver().session() as session:
result = session.run(query)
records = [record.data() for record in result]
if not records:
console.print("[yellow]No results to visualize.[/yellow]")
return # finally block will close driver
visualize_cypher_results(records, query)
except Exception as e:
console.print(
f"[bold red]An error occurred while executing query:[/bold red] {e}"
)
finally:
db_manager.close_driver()
import webbrowser
import urllib.parse
from ..viz.server import run_server, set_db_manager
def visualize_helper(repo_path: Optional[str] = None, port: int = 8000):
""" "Generates an interactive visualization using the Playground UI."""
services = _initialize_services()
if not all(services):
return
db_manager, _, _ = services
# Set the DB manager for the server
set_db_manager(db_manager)
# Determine the static directory (built React app)
static_dir = Path(__file__).parent.parent / "viz" / "dist"
if not static_dir.exists():
console.print(
"[yellow]Warning: Visualizer UI assets not found in package. Using fallback static dir.[/yellow]"
)
# Fallback for development
static_dir = Path.cwd() / "website" / "dist"
# Construct the URL
backend_url = f"http://localhost:{port}"
params = {"backend": backend_url}
if repo_path:
params["repo_path"] = str(Path(repo_path).resolve())
query_string = urllib.parse.urlencode(params)
visualization_url = f"{backend_url}/playground?{query_string}"
console.print(f"[green]Starting visualizer server on {backend_url}...[/green]")
console.print(f"[cyan]Opening Playground UI:[/cyan] {visualization_url}")
# Open browser in a separate thread/process if possible, or just before starting server
def open_browser():
import time
time.sleep(1.5) # Give the server a moment to start
webbrowser.open(visualization_url)
import threading
threading.Thread(target=open_browser, daemon=True).start()
try:
run_server(host="127.0.0.1", port=port, static_dir=str(static_dir))
except Exception as e:
console.print(
f"[bold red]An error occurred while running the server:[/bold red] {e}"
)
finally:
db_manager.close_driver()
def _visualize_falkordb(db_manager):
console.print(
"[dim]Generating FalkorDB visualization (showing up to 500 relationships)...[/dim]"
)
try:
data_nodes = []
data_edges = []
with db_manager.get_driver().session() as session:
# Fetch nodes and edges
q = "MATCH (n)-[r]->(m) RETURN n, r, m LIMIT 500"
result = session.run(q)
seen_nodes = set()
for record in result:
# record values are Node/Relationship objects from falkordb client
n = record["n"]
r = record["r"]
m = record["m"]
# Process Node helper
def process_node(node):
nid = getattr(node, "id", -1)
labels = getattr(node, "labels", [])
lbl = list(labels)[0] if labels else "Node"
props = getattr(node, "properties", {})
name = props.get("name", str(nid))
if nid not in seen_nodes:
seen_nodes.add(nid)
color = "#97c2fc" # Default blue
if "Repository" in labels:
color = "#ffb3ba" # Red
elif "File" in labels:
color = "#baffc9" # Green
elif "Class" in labels:
color = "#bae1ff" # Light Blue
elif "Function" in labels:
color = "#ffffba" # Yellow
elif "Package" in labels:
color = "#ffdfba" # Orange
data_nodes.append(
{
"id": nid,
"label": name,
"group": lbl,
"title": str(props),
"color": color,
}
)
return nid
nid = process_node(n)
mid = process_node(m)
# Check Edge
e_type = getattr(r, "relation", "") or getattr(r, "type", "REL")
data_edges.append(
{"from": nid, "to": mid, "label": e_type, "arrows": "to"}
)
filename = "codegraph_viz.html"
html_content = f"""
<!DOCTYPE html>
<html>
<head>
<title>CodeGraphContext Visualization</title>
<script type="text/javascript" src="https://unpkg.com/vis-network/standalone/umd/vis-network.min.js"></script>
<style type="text/css">
#mynetwork {{
width: 100%;
height: 100vh;
border: 1px solid lightgray;
}}
</style>
</head>
<body>
<div id="mynetwork"></div>
<script type="text/javascript">
var nodes = new vis.DataSet({json.dumps(data_nodes)});
var edges = new vis.DataSet({json.dumps(data_edges)});
var container = document.getElementById('mynetwork');
var data = {{ nodes: nodes, edges: edges }};
var options = {{
nodes: {{ shape: 'dot', size: 16 }},
physics: {{ stabilization: false }},
layout: {{ improvedLayout: false }}
}};
var network = new vis.Network(container, data, options);
</script>
</body>
</html>
"""
out_path = Path(filename).resolve()
with open(out_path, "w") as f:
f.write(html_content)
console.print(f"[green]Visualization generated at:[/green] {out_path}")
console.print("Opening in default browser...")
webbrowser.open(f"file://{out_path}")
except Exception as e:
console.print(f"[bold red]Visualization failed:[/bold red] {e}")
import traceback
traceback.print_exc()
finally:
db_manager.close_driver()
def _visualize_kuzudb(db_manager):
console.print(
"[dim]Generating KùzuDB visualization (showing up to 500 relationships)...[/dim]"
)
try:
data_nodes = []
data_edges = []
with db_manager.get_driver().session() as session:
# Fetch nodes and edges
# KùzuDB returns dicts for n, r, m in the result
q = "MATCH (n)-[r]->(m) RETURN n, r, m LIMIT 500"
result = session.run(q)
seen_nodes = set()
# Helper to extract Node ID and props
def process_node(node):
uid = None
lbl = "Node"
props = {}
# Handle Kuzu Node Object (processed by wrapper)
if hasattr(node, "properties"):
props = node.properties or {}
if hasattr(node, "labels") and node.labels:
lbl = node.labels[0]
if hasattr(node, "id"):
uid = str(node.id)
# Handle Dictionary (raw Kuzu result)
elif isinstance(node, dict):
if "_id" in node:
uid = f"{node['_id']['table']}_{node['_id']['offset']}"
lbl = node.get("_label", "Node")
props = {k: v for k, v in node.items() if not k.startswith("_")}
if not uid:
uid = str(uuid.uuid4())
name = props.get("name", str(uid))
if uid not in seen_nodes:
seen_nodes.add(uid)
color = "#97c2fc" # Default blue
if "Repository" == lbl:
color = "#ffb3ba"
elif "File" == lbl:
color = "#baffc9"
elif "Class" == lbl:
color = "#bae1ff"
elif "Function" == lbl:
color = "#ffffba"
elif "Module" == lbl:
color = "#ffdfba"
data_nodes.append(
{
"id": uid,
"label": name,
"group": lbl,
"title": str(props),
"color": color,
}
)
return uid
# Iterate results
for record in result:
# record is dict-like access to row items
n = record["n"]
r = record["r"]
m = record["m"]
nid = process_node(n)
mid = process_node(m)
# Process Edge
e_type = "REL"
if hasattr(r, "type"):
e_type = r.type
elif isinstance(r, dict):
e_type = r.get("_label", "REL")
elif hasattr(r, "label"): # Some versions
e_type = r.label
data_edges.append(
{"from": nid, "to": mid, "label": e_type, "arrows": "to"}
)
filename = "codegraph_viz.html"
html_content = f"""
<!DOCTYPE html>
<html>
<head>
<title>CodeGraphContext KùzuDB Visualization</title>
<script type="text/javascript" src="https://unpkg.com/vis-network/standalone/umd/vis-network.min.js"></script>
<style type="text/css">
#mynetwork {{
width: 100%;
height: 100vh;
border: 1px solid lightgray;
}}
</style>
</head>
<body>
<div id="mynetwork"></div>
<script type="text/javascript">
var nodes = new vis.DataSet({json.dumps(data_nodes)});
var edges = new vis.DataSet({json.dumps(data_edges)});
var container = document.getElementById('mynetwork');
var data = {{ nodes: nodes, edges: edges }};
var options = {{
nodes: {{ shape: 'dot', size: 16 }},
physics: {{ stabilization: false }},
layout: {{ improvedLayout: false }}
}};
var network = new vis.Network(container, data, options);
</script>
</body>
</html>
"""
out_path = Path(filename).resolve()
with open(out_path, "w") as f:
f.write(html_content)
console.print(f"[green]Visualization generated at:[/green] {out_path}")
console.print("Opening in default browser...")
webbrowser.open(f"file://{out_path}")
except Exception as e:
console.print(f"[bold red]Visualization failed:[/bold red] {e}")
import traceback
traceback.print_exc()
finally:
db_manager.close_driver()
def reindex_helper(path: str):
"""Force re-index by deleting and rebuilding the repository."""
time_start = time.time()
services = _initialize_services()
if not all(services):
return
db_manager, graph_builder, code_finder = services
path_obj = Path(path).resolve()
if not path_obj.exists():
console.print(f"[red]Error: Path does not exist: {path_obj}[/red]")
db_manager.close_driver()
return
indexed_repos = code_finder.list_indexed_repositories()
repo_exists = any(Path(repo["path"]).resolve() == path_obj for repo in indexed_repos)
if repo_exists:
console.print(f"[yellow]Deleting existing index for: {path_obj}[/yellow]")
try:
graph_builder.delete_repository_from_graph(str(path_obj))
console.print("[green]✓[/green] Deleted old index")
except Exception as e:
console.print(f"[red]Error deleting old index: {e}[/red]")
db_manager.close_driver()
return
console.print(f"[cyan]Re-indexing: {path_obj}[/cyan]")
try:
asyncio.run(
_run_index_with_progress(graph_builder, path_obj, is_dependency=False)
)
time_end = time.time()
elapsed = time_end - time_start
console.print(
f"[green]Successfully re-indexed: {path} in {elapsed:.2f} seconds[/green]"
)
except Exception as e:
_print_cli_exception("An error occurred during re-indexing:", e)
finally:
db_manager.close_driver()
def update_helper(path: str):
"""Update/refresh index for a path (alias for reindex)."""
console.print("[cyan]Updating repository index...[/cyan]")
reindex_helper(path)
def clean_helper():
"""Remove orphaned nodes and relationships from the database."""
services = _initialize_services()
if not all(services):
return
db_manager, _, _ = services
console.print("[cyan]🧹 Cleaning database (removing orphaned nodes)...[/cyan]")
try:
# Determine if we're using FalkorDB or Neo4j for query optimization
db_type = db_manager.__class__.__name__
is_falkordb = "Falkor" in db_type
total_deleted = 0
batch_size = 1000
with db_manager.get_driver().session() as session:
# Keep deleting orphaned nodes in batches until none are found
while True:
if is_falkordb:
# FalkorDB-compatible query using OPTIONAL MATCH
query = """
MATCH (n)
WHERE NOT (n:Repository)
OPTIONAL MATCH path = (n)-[*..10]-(r:Repository)
WITH n, path
WHERE path IS NULL
WITH n LIMIT $batch_size
DETACH DELETE n
RETURN count(n) as deleted
"""
else:
# Neo4j optimized query using NOT EXISTS with bounded path
# This is much faster than OPTIONAL MATCH with variable-length paths
query = """
MATCH (n)
WHERE NOT (n:Repository)
AND NOT EXISTS {
MATCH (n)-[*..10]-(r:Repository)
}
WITH n LIMIT $batch_size
DETACH DELETE n
RETURN count(n) as deleted
"""
result = session.run(query, batch_size=batch_size)
record = result.single()
deleted_count = record["deleted"] if record else 0
total_deleted += deleted_count
if deleted_count == 0:
break
console.print(
f"[dim]Deleted {deleted_count} orphaned nodes (batch)...[/dim]"
)
if total_deleted > 0:
console.print(
f"[green]✓[/green] Deleted {total_deleted} orphaned nodes total"
)
else:
console.print("[green]✓[/green] No orphaned nodes found")
# Clean up any duplicate relationships (if any)
console.print("[dim]Checking for duplicate relationships...[/dim]")
# Note: This is database-specific and might not work for all backends
console.print("[green]✅ Database cleanup complete![/green]")
except Exception as e:
console.print(f"[bold red]An error occurred during cleanup:[/bold red] {e}")
finally:
db_manager.close_driver()
def stats_helper(path: str = None):
"""Show indexing statistics for a repository or overall."""
services = _initialize_services()
if not all(services):
return
db_manager, _, code_finder = services
try:
if path:
# Stats for specific repository
path_obj = Path(path).resolve()
console.print(f"[cyan]📊 Statistics for: {path_obj}[/cyan]\n")
with db_manager.get_driver().session() as session:
# Get repository node
repo_query = """
MATCH (r:Repository {path: $path})
RETURN r
"""
result = session.run(repo_query, path=str(path_obj))
if not result.single():
console.print(f"[red]Repository not found: {path_obj}[/red]")
return
# Get stats
# Get stats using separate queries to handle depth and avoid Cartesian products
# 1. Files
file_query = "MATCH (r:Repository {path: $path})-[:CONTAINS*]->(f:File) RETURN count(f) as c"
file_count = session.run(file_query, path=str(path_obj)).single()["c"]
# 2. Functions (including methods in classes)