forked from taylorwilsdon/google_workspace_mcp
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdocs_tools.py
More file actions
2460 lines (2138 loc) · 92.8 KB
/
docs_tools.py
File metadata and controls
2460 lines (2138 loc) · 92.8 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
"""
Google Docs MCP Tools
This module provides MCP tools for interacting with Google Docs API and managing Google Docs via Drive.
"""
import logging
import asyncio
import io
import inspect
import re
from typing import List, Any, Optional
from googleapiclient.errors import HttpError
from googleapiclient.http import MediaIoBaseDownload, MediaIoBaseUpload
# Auth & server utilities
from auth.service_decorator import require_google_service, require_multiple_services
from core.utils import extract_office_xml_text, handle_http_errors, UserInputError
from core.server import server
from core.comments import create_comment_tools
# Import helper functions for document operations
from gdocs.docs_helpers import (
create_insert_text_request,
create_delete_range_request,
create_format_text_request,
create_find_replace_request,
create_insert_table_request,
create_insert_page_break_request,
create_insert_image_request,
create_bullet_list_request,
create_insert_doc_tab_request,
create_update_doc_tab_request,
create_delete_doc_tab_request,
validate_suggestions_view_mode,
create_update_paragraph_style_request,
)
# Import document structure and table utilities
from gdocs.docs_structure import (
parse_document_structure,
find_tables,
analyze_document_complexity,
)
from gdocs.docs_tables import extract_table_as_data
from gdocs.docs_markdown import (
convert_doc_to_markdown,
format_comments_inline,
format_comments_appendix,
parse_drive_comments,
)
from gdocs.operation_schemas import BatchDocOperations
# Import operation managers for complex business logic
from gdocs.managers import (
TableOperationManager,
HeaderFooterManager,
ValidationManager,
BatchOperationManager,
)
import json
logger = logging.getLogger(__name__)
HEADER_FOOTER_RUNTIME_CANARY = "docs-hf-canary-20260328b"
@server.tool()
@handle_http_errors("search_docs", is_read_only=True, service_type="docs")
@require_google_service("drive", "drive_read")
async def search_docs(
service: Any,
user_google_email: str,
query: str,
page_size: int = 10,
) -> str:
"""
Searches for Google Docs by name using Drive API (mimeType filter).
Returns:
str: A formatted list of Google Docs matching the search query.
"""
logger.info(f"[search_docs] Email={user_google_email}, Query='{query}'")
escaped_query = query.replace("'", "\\'")
response = await asyncio.to_thread(
service.files()
.list(
q=f"name contains '{escaped_query}' and mimeType='application/vnd.google-apps.document' and trashed=false",
pageSize=page_size,
fields="files(id, name, createdTime, modifiedTime, webViewLink)",
supportsAllDrives=True,
includeItemsFromAllDrives=True,
)
.execute
)
files = response.get("files", [])
if not files:
return f"No Google Docs found matching '{query}'."
output = [f"Found {len(files)} Google Docs matching '{query}':"]
for f in files:
output.append(
f"- {f['name']} (ID: {f['id']}) Modified: {f.get('modifiedTime')} Link: {f.get('webViewLink')}"
)
return "\n".join(output)
@server.tool()
@handle_http_errors("get_doc_content", is_read_only=True, service_type="docs")
@require_multiple_services(
[
{
"service_type": "drive",
"scopes": "drive_read",
"param_name": "drive_service",
},
{"service_type": "docs", "scopes": "docs_read", "param_name": "docs_service"},
]
)
async def get_doc_content(
drive_service: Any,
docs_service: Any,
user_google_email: str,
document_id: str,
suggestions_view_mode: str = "DEFAULT_FOR_CURRENT_ACCESS",
) -> str:
"""
Retrieves content of a Google Doc or a Drive file (like .docx) identified by document_id.
- Native Google Docs: Fetches content via Docs API.
- Office files (.docx, etc.) stored in Drive: Downloads via Drive API and extracts text.
Args:
user_google_email: User's Google email address
document_id: ID of the Google Doc (or full URL)
suggestions_view_mode: How to render suggestions in the returned content:
- "DEFAULT_FOR_CURRENT_ACCESS": Default based on user's access level
- "SUGGESTIONS_INLINE": Suggested changes appear inline in the document
- "PREVIEW_SUGGESTIONS_ACCEPTED": Preview as if all suggestions were accepted
- "PREVIEW_WITHOUT_SUGGESTIONS": Preview as if all suggestions were rejected
Returns:
str: The document content with metadata header.
"""
validation_error = validate_suggestions_view_mode(suggestions_view_mode)
if validation_error:
return validation_error
logger.info(
f"[get_doc_content] Invoked. Document/File ID: '{document_id}' for user '{user_google_email}'"
)
file_metadata = await asyncio.to_thread(
drive_service.files()
.get(
fileId=document_id,
fields="id, name, mimeType, webViewLink",
supportsAllDrives=True,
)
.execute
)
mime_type = file_metadata.get("mimeType", "")
file_name = file_metadata.get("name", "Unknown File")
web_view_link = file_metadata.get("webViewLink", "#")
logger.info(
f"[get_doc_content] File '{file_name}' (ID: {document_id}) has mimeType: '{mime_type}'"
)
body_text = ""
if mime_type == "application/vnd.google-apps.document":
logger.info("[get_doc_content] Processing as native Google Doc.")
doc_data = await asyncio.to_thread(
docs_service.documents()
.get(
documentId=document_id,
includeTabsContent=True,
suggestionsViewMode=suggestions_view_mode,
)
.execute
)
TAB_HEADER_FORMAT = "\n--- TAB: {tab_name} (ID: {tab_id}) ---\n"
def extract_text_from_elements(elements, tab_name=None, tab_id=None, depth=0):
"""Extract text from document elements (paragraphs, tables, etc.)"""
if depth > 5:
return ""
text_lines = []
if tab_name:
text_lines.append(
TAB_HEADER_FORMAT.format(tab_name=tab_name, tab_id=tab_id)
)
for element in elements:
if "paragraph" in element:
paragraph = element.get("paragraph", {})
para_elements = paragraph.get("elements", [])
current_line_text = ""
for pe in para_elements:
text_run = pe.get("textRun", {})
if text_run and "content" in text_run:
current_line_text += text_run["content"]
if current_line_text.strip():
text_lines.append(current_line_text)
elif "table" in element:
# Handle table content
table = element.get("table", {})
table_rows = table.get("tableRows", [])
for row in table_rows:
row_cells = row.get("tableCells", [])
for cell in row_cells:
cell_content = cell.get("content", [])
cell_text = extract_text_from_elements(
cell_content, depth=depth + 1
)
if cell_text.strip():
text_lines.append(cell_text)
return "".join(text_lines)
def process_tab_hierarchy(tab, level=0):
"""Process a tab and its nested child tabs recursively"""
tab_text = ""
if "documentTab" in tab:
props = tab.get("tabProperties", {})
tab_title = props.get("title", "Untitled Tab")
tab_id = props.get("tabId", "Unknown ID")
if level > 0:
tab_title = " " * level + f"{tab_title}"
tab_body = tab.get("documentTab", {}).get("body", {}).get("content", [])
tab_text += extract_text_from_elements(tab_body, tab_title, tab_id)
child_tabs = tab.get("childTabs", [])
for child_tab in child_tabs:
tab_text += process_tab_hierarchy(child_tab, level + 1)
return tab_text
processed_text_lines = []
body_elements = doc_data.get("body", {}).get("content", [])
main_content = extract_text_from_elements(body_elements)
if main_content.strip():
processed_text_lines.append(main_content)
tabs = doc_data.get("tabs", [])
for tab in tabs:
tab_content = process_tab_hierarchy(tab)
if tab_content.strip():
processed_text_lines.append(tab_content)
body_text = "".join(processed_text_lines)
else:
logger.info(
f"[get_doc_content] Processing as Drive file (e.g., .docx, other). MimeType: {mime_type}"
)
export_mime_type_map = {
# Example: "application/vnd.google-apps.spreadsheet"z: "text/csv",
# Native GSuite types that are not Docs would go here if this function
# was intended to export them. For .docx, direct download is used.
}
effective_export_mime = export_mime_type_map.get(mime_type)
request_obj = (
drive_service.files().export_media(
fileId=document_id,
mimeType=effective_export_mime,
supportsAllDrives=True,
)
if effective_export_mime
else drive_service.files().get_media(
fileId=document_id, supportsAllDrives=True
)
)
fh = io.BytesIO()
downloader = MediaIoBaseDownload(fh, request_obj)
loop = asyncio.get_event_loop()
done = False
while not done:
status, done = await loop.run_in_executor(None, downloader.next_chunk)
file_content_bytes = fh.getvalue()
office_text = extract_office_xml_text(file_content_bytes, mime_type)
if office_text:
body_text = office_text
else:
try:
body_text = file_content_bytes.decode("utf-8")
except UnicodeDecodeError:
body_text = (
f"[Binary or unsupported text encoding for mimeType '{mime_type}' - "
f"{len(file_content_bytes)} bytes]"
)
header = (
f'File: "{file_name}" (ID: {document_id}, Type: {mime_type})\n'
f"Link: {web_view_link}\n\n--- CONTENT ---\n"
)
return header + body_text
@server.tool()
@handle_http_errors("list_docs_in_folder", is_read_only=True, service_type="docs")
@require_google_service("drive", "drive_read")
async def list_docs_in_folder(
service: Any, user_google_email: str, folder_id: str = "root", page_size: int = 100
) -> str:
"""
Lists Google Docs within a specific Drive folder.
Returns:
str: A formatted list of Google Docs in the specified folder.
"""
logger.info(
f"[list_docs_in_folder] Invoked. Email: '{user_google_email}', Folder ID: '{folder_id}'"
)
rsp = await asyncio.to_thread(
service.files()
.list(
q=f"'{folder_id}' in parents and mimeType='application/vnd.google-apps.document' and trashed=false",
pageSize=page_size,
fields="files(id, name, modifiedTime, webViewLink)",
supportsAllDrives=True,
includeItemsFromAllDrives=True,
)
.execute
)
items = rsp.get("files", [])
if not items:
return f"No Google Docs found in folder '{folder_id}'."
out = [f"Found {len(items)} Docs in folder '{folder_id}':"]
for f in items:
out.append(
f"- {f['name']} (ID: {f['id']}) Modified: {f.get('modifiedTime')} Link: {f.get('webViewLink')}"
)
return "\n".join(out)
@server.tool()
@handle_http_errors("create_doc", service_type="docs")
@require_google_service("docs", "docs_write")
async def create_doc(
service: Any,
user_google_email: str,
title: str,
content: str = "",
) -> str:
"""
Creates a new Google Doc and optionally inserts initial content.
After creation, the document body starts at index 1. A new empty doc
has total length 2 (one section break at index 0, one newline at index 1).
To build a rich document after creation, use batch_update_doc with
insert_text operations using end_of_segment=true to append content
sequentially without calculating indices. Then call inspect_doc_structure
to get exact positions before applying formatting in a separate batch call.
Args:
user_google_email: User's Google email address
title: Title of the new document
content: Optional initial plain text content to insert
Returns:
str: Confirmation message with document ID, link, and initial document state.
"""
logger.info(f"[create_doc] Invoked. Email: '{user_google_email}', Title='{title}'")
doc = await asyncio.to_thread(
service.documents().create(body={"title": title}).execute
)
doc_id = doc.get("documentId")
if content:
requests = [{"insertText": {"location": {"index": 1}, "text": content}}]
await asyncio.to_thread(
service.documents()
.batchUpdate(documentId=doc_id, body={"requests": requests})
.execute
)
link = f"https://docs.google.com/document/d/{doc_id}/edit"
if content:
content_note = f"Initial content: {len(content)} characters inserted."
else:
content_note = "Document is empty (body starts at index 1, total length 2)."
msg = (
f"Created Google Doc '{title}' (ID: {doc_id}) for {user_google_email}. "
f"{content_note} "
f"Use batch_update_doc with end_of_segment=true to append content. "
f"Link: {link}"
)
logger.info(
f"Successfully created Google Doc '{title}' (ID: {doc_id}) for {user_google_email}. Link: {link}"
)
return msg
@server.tool()
@handle_http_errors("modify_doc_text", service_type="docs")
@require_google_service("docs", "docs_write")
async def modify_doc_text(
service: Any,
user_google_email: str,
document_id: str,
start_index: int,
end_index: int = None,
text: str = None,
tab_id: str = None,
segment_id: str = None,
end_of_segment: bool = False,
bold: bool = None,
italic: bool = None,
underline: bool = None,
strikethrough: bool = None,
font_size: int = None,
font_family: str = None,
font_weight: int = None,
text_color: str = None,
background_color: str = None,
link_url: str = None,
clear_link: bool = None,
baseline_offset: str = None,
small_caps: bool = None,
) -> str:
"""
Modifies text in a Google Doc - can insert/replace text and/or apply formatting in a single operation.
TIP: To append text to the end of the document without calculating indices,
set end_of_segment=true. This avoids index calculation errors.
For ordinary header/footer text, prefer update_doc_headers_footers.
Only pass segment_id when you already have a real header/footer/footnote
segment ID from inspect_doc_structure output. Do not guess IDs such as
"kix.header" or "kix.footer".
Args:
user_google_email: User's Google email address
document_id: ID of the document to update
start_index: Start position for operation using Docs API indices from
inspect_doc_structure. For the main body, 0 is also accepted as an
alias for the first writable position.
end_index: End position for text replacement/formatting (if not provided with text, text is inserted)
text: New text to insert or replace with (optional - can format existing text without changing it)
tab_id: Optional document tab ID to target
segment_id: Optional header/footer/footnote segment ID to target
end_of_segment: Insert text at the end of the targeted segment instead of start_index
bold: Whether to make text bold (True/False/None to leave unchanged)
italic: Whether to make text italic (True/False/None to leave unchanged)
underline: Whether to underline text (True/False/None to leave unchanged)
strikethrough: Whether to strike through text (True/False/None to leave unchanged)
font_size: Font size in points
font_family: Font family name (e.g., "Arial", "Times New Roman")
font_weight: Font weight (100-900 in steps of 100; requires font_family)
text_color: Foreground text color (#RRGGBB)
background_color: Background/highlight color (#RRGGBB)
link_url: Hyperlink URL (http/https)
clear_link: Remove hyperlink from the target range
baseline_offset: One of NONE, SUPERSCRIPT, SUBSCRIPT
small_caps: Whether to apply small caps
Returns:
str: Confirmation message with operation details
"""
logger.info(
f"[modify_doc_text] Doc={document_id}, start={start_index}, end={end_index}, text={text is not None}, "
f"formatting={any(p is not None for p in [bold, italic, underline, strikethrough, font_size, font_family, font_weight, text_color, background_color, link_url, clear_link, baseline_offset, small_caps])}"
)
# Input validation
validator = ValidationManager()
is_valid, error_msg = validator.validate_document_id(document_id)
if not is_valid:
return f"Error: {error_msg}"
# Validate that we have something to do
formatting_params = [
bold,
italic,
underline,
strikethrough,
font_size,
font_family,
font_weight,
text_color,
background_color,
link_url,
clear_link,
baseline_offset,
small_caps,
]
if text is None and not any(p is not None for p in formatting_params):
return "Error: Must provide either 'text' to insert/replace, or formatting parameters (bold, italic, underline, strikethrough, font_size, font_family, text_color, background_color, link_url)."
# Validate text formatting params if provided
if any(p is not None for p in formatting_params):
is_valid, error_msg = validator.validate_text_formatting_params(
bold,
italic,
underline,
strikethrough,
font_size,
font_family,
font_weight,
text_color,
background_color,
link_url,
clear_link,
baseline_offset,
small_caps,
)
if not is_valid:
return f"Error: {error_msg}"
# For formatting, we need end_index
if end_index is None:
return "Error: 'end_index' is required when applying formatting."
if end_of_segment:
return "Error: end_of_segment cannot be used when applying formatting."
is_valid, error_msg = validator.validate_index_range(start_index, end_index)
if not is_valid:
return f"Error: {error_msg}"
requests = []
operations = []
# Handle text insertion/replacement
if text is not None:
if end_index is not None and end_index > start_index:
# Text replacement
if end_of_segment:
return "Error: end_of_segment cannot be combined with text replacement."
if start_index == 0 and segment_id is None and tab_id is None:
# Special case: Cannot delete at index 0 (first section break)
# Instead, we insert new text at index 1 and then delete the old text
requests.append(
create_insert_text_request(1, text, tab_id, segment_id=segment_id)
)
adjusted_end = end_index + len(text)
requests.append(
create_delete_range_request(
1 + len(text), adjusted_end, tab_id, segment_id=segment_id
)
)
operations.append(
f"Replaced text from index {start_index} to {end_index}"
)
else:
# Normal replacement: delete old text, then insert new text
requests.extend(
[
create_delete_range_request(
start_index, end_index, tab_id, segment_id=segment_id
),
create_insert_text_request(
start_index, text, tab_id, segment_id=segment_id
),
]
)
operations.append(
f"Replaced text from index {start_index} to {end_index}"
)
else:
# Text insertion
actual_index = (
1
if start_index == 0
and not end_of_segment
and segment_id is None
and tab_id is None
else start_index
)
requests.append(
create_insert_text_request(
None if end_of_segment else actual_index,
text,
tab_id,
segment_id=segment_id,
end_of_segment=end_of_segment,
)
)
if end_of_segment:
operations.append(
f"Inserted text at end of segment '{segment_id or 'body'}'"
)
else:
operations.append(f"Inserted text at index {start_index}")
# Handle formatting
if any(p is not None for p in formatting_params):
# Adjust range for formatting based on text operations
format_start = start_index
format_end = end_index
if text is not None:
if end_index is not None and end_index > start_index:
# Text was replaced - format the new text
format_end = start_index + len(text)
else:
# Text was inserted - format the inserted text
actual_index = 1 if start_index == 0 else start_index
format_start = actual_index
format_end = actual_index + len(text)
# Handle special case for formatting at index 0
if format_start == 0 and segment_id is None and tab_id is None:
format_start = 1
if format_end is not None and format_end <= format_start:
format_end = format_start + 1
requests.append(
create_format_text_request(
format_start,
format_end,
bold,
italic,
underline,
strikethrough,
font_size,
font_family,
font_weight,
text_color,
background_color,
link_url,
clear_link,
baseline_offset,
small_caps,
tab_id,
segment_id,
)
)
format_details = [
f"{name}={value}"
for name, value in [
("bold", bold),
("italic", italic),
("underline", underline),
("strikethrough", strikethrough),
("font_size", font_size),
("font_family", font_family),
("font_weight", font_weight),
("text_color", text_color),
("background_color", background_color),
("link_url", link_url),
("clear_link", clear_link),
("baseline_offset", baseline_offset),
("small_caps", small_caps),
]
if value is not None
]
operations.append(
f"Applied formatting ({', '.join(format_details)}) to range {format_start}-{format_end}"
)
try:
await asyncio.to_thread(
service.documents()
.batchUpdate(documentId=document_id, body={"requests": requests})
.execute
)
except HttpError as error:
raise _rewrite_modify_doc_text_http_error(error, segment_id) from error
link = f"https://docs.google.com/document/d/{document_id}/edit"
operation_summary = "; ".join(operations)
text_info = f" Text length: {len(text)} characters." if text else ""
return f"{operation_summary} in document {document_id}.{text_info} Link: {link}"
@server.tool()
@handle_http_errors("find_and_replace_doc", service_type="docs")
@require_google_service("docs", "docs_write")
async def find_and_replace_doc(
service: Any,
user_google_email: str,
document_id: str,
find_text: str,
replace_text: str,
match_case: bool = False,
tab_id: Optional[str] = None,
) -> str:
"""
Finds and replaces text throughout a Google Doc. No index calculation required.
This is the safest way to update specific text in a document because it
does not require knowing any indices. Use this tool when you need to:
- Replace placeholder text (e.g., {{TITLE}}) with real content
- Update specific words or phrases throughout the document
- Make targeted text changes without risk of index errors
For building documents from scratch, consider inserting text with unique
placeholders via batch_update_doc, then using this tool to replace them.
Args:
user_google_email: User's Google email address
document_id: ID of the document to update
find_text: Text to search for
replace_text: Text to replace with
match_case: Whether to match case exactly
tab_id: Optional ID of the tab to target
Returns:
str: Confirmation message with replacement count
"""
logger.info(
f"[find_and_replace_doc] Doc={document_id}, find='{find_text}', replace='{replace_text}', tab='{tab_id}'"
)
requests = [
create_find_replace_request(find_text, replace_text, match_case, tab_id)
]
result = await asyncio.to_thread(
service.documents()
.batchUpdate(documentId=document_id, body={"requests": requests})
.execute
)
# Extract number of replacements from response
replacements = 0
if "replies" in result and result["replies"]:
reply = result["replies"][0]
if "replaceAllText" in reply:
replacements = reply["replaceAllText"].get("occurrencesChanged", 0)
link = f"https://docs.google.com/document/d/{document_id}/edit"
return f"Replaced {replacements} occurrence(s) of '{find_text}' with '{replace_text}' in document {document_id}. Link: {link}"
@server.tool()
@handle_http_errors("insert_doc_elements", service_type="docs")
@require_google_service("docs", "docs_write")
async def insert_doc_elements(
service: Any,
user_google_email: str,
document_id: str,
element_type: str,
index: int,
rows: int = None,
columns: int = None,
list_type: str = None,
text: str = None,
) -> str:
"""
Inserts structural elements like tables, lists, or page breaks into a Google Doc.
Args:
user_google_email: User's Google email address
document_id: ID of the document to update
element_type: Type of element to insert ("table", "list", "page_break")
index: Position to insert element (0-based)
rows: Number of rows for table (required for table)
columns: Number of columns for table (required for table)
list_type: Type of list ("UNORDERED", "ORDERED") (required for list)
text: Initial text content for list items
Returns:
str: Confirmation message with insertion details
"""
logger.info(
f"[insert_doc_elements] Doc={document_id}, type={element_type}, index={index}"
)
# Handle the special case where we can't insert at the first section break
# If index is 0, bump it to 1 to avoid the section break
if index == 0:
logger.debug("Adjusting index from 0 to 1 to avoid first section break")
index = 1
requests = []
if element_type == "table":
if not rows or not columns:
return "Error: 'rows' and 'columns' parameters are required for table insertion."
requests.append(create_insert_table_request(index, rows, columns))
description = f"table ({rows}x{columns})"
elif element_type == "list":
if not list_type:
return "Error: 'list_type' parameter is required for list insertion ('UNORDERED' or 'ORDERED')."
if not text:
text = "List item"
# Insert text first, then create list
requests.extend(
[
create_insert_text_request(index, text + "\n"),
create_bullet_list_request(index, index + len(text), list_type),
]
)
description = f"{list_type.lower()} list"
elif element_type == "page_break":
requests.append(create_insert_page_break_request(index))
description = "page break"
else:
return f"Error: Unsupported element type '{element_type}'. Supported types: 'table', 'list', 'page_break'."
await asyncio.to_thread(
service.documents()
.batchUpdate(documentId=document_id, body={"requests": requests})
.execute
)
link = f"https://docs.google.com/document/d/{document_id}/edit"
return f"Inserted {description} at index {index} in document {document_id}. Link: {link}"
@server.tool()
@handle_http_errors("insert_doc_image", service_type="docs")
@require_multiple_services(
[
{"service_type": "docs", "scopes": "docs_write", "param_name": "docs_service"},
{
"service_type": "drive",
"scopes": "drive_read",
"param_name": "drive_service",
},
]
)
async def insert_doc_image(
docs_service: Any,
drive_service: Any,
user_google_email: str,
document_id: str,
image_source: str,
index: int,
width: int = 0,
height: int = 0,
) -> str:
"""
Inserts an image into a Google Doc from Drive or a URL.
Args:
user_google_email: User's Google email address
document_id: ID of the document to update
image_source: Drive file ID or public image URL
index: Position to insert image (0-based)
width: Image width in points (optional)
height: Image height in points (optional)
Returns:
str: Confirmation message with insertion details
"""
logger.info(
f"[insert_doc_image] Doc={document_id}, source={image_source}, index={index}"
)
# Handle the special case where we can't insert at the first section break
# If index is 0, bump it to 1 to avoid the section break
if index == 0:
logger.debug("Adjusting index from 0 to 1 to avoid first section break")
index = 1
# Determine if source is a Drive file ID or URL
is_drive_file = not (
image_source.startswith("http://") or image_source.startswith("https://")
)
if is_drive_file:
# Verify Drive file exists and get metadata
try:
file_metadata = await asyncio.to_thread(
drive_service.files()
.get(
fileId=image_source,
fields="id, name, mimeType",
supportsAllDrives=True,
)
.execute
)
mime_type = file_metadata.get("mimeType", "")
if not mime_type.startswith("image/"):
return f"Error: File {image_source} is not an image (MIME type: {mime_type})."
image_uri = f"https://drive.google.com/uc?id={image_source}"
source_description = f"Drive file {file_metadata.get('name', image_source)}"
except Exception as e:
return f"Error: Could not access Drive file {image_source}: {str(e)}"
else:
image_uri = image_source
source_description = "URL image"
# Use helper to create image request
requests = [create_insert_image_request(index, image_uri, width, height)]
await asyncio.to_thread(
docs_service.documents()
.batchUpdate(documentId=document_id, body={"requests": requests})
.execute
)
size_info = ""
if width or height:
size_info = f" (size: {width or 'auto'}x{height or 'auto'} points)"
link = f"https://docs.google.com/document/d/{document_id}/edit"
return f"Inserted {source_description}{size_info} at index {index} in document {document_id}. Link: {link}"
@server.tool()
@handle_http_errors("update_doc_headers_footers", service_type="docs")
@require_google_service("docs", "docs_write")
async def update_doc_headers_footers(
service: Any,
user_google_email: str,
document_id: str,
section_type: str,
content: str,
header_footer_type: str = "DEFAULT",
) -> str:
"""
Safely creates or updates header/footer text in a Google Doc.
This is the default tool for header/footer content. Do NOT use
batch_update_doc with create_header_footer just to set header/footer text;
that low-level operation is only for advanced section-break workflows and
can fail when the default header/footer already exists.
This tool handles both creation and update in one call:
- If the header/footer does not exist, it is automatically created first.
- If the header/footer already exists, its content is replaced.
You do NOT need to create a header/footer separately before calling this tool.
Simply call it with the desired content and it will work whether the
header/footer exists or not.
Args:
user_google_email: User's Google email address
document_id: ID of the document to update
section_type: Type of section to create or update ("header" or "footer")
content: Text content for the header/footer
header_footer_type: Type of header/footer ("DEFAULT", "FIRST_PAGE_ONLY", "EVEN_PAGE")
Returns:
str: Confirmation message with update details
"""
logger.info(f"[update_doc_headers_footers] Doc={document_id}, type={section_type}")
# Input validation
validator = ValidationManager()
is_valid, error_msg = validator.validate_document_id(document_id)
if not is_valid:
return f"Error: {error_msg}"
is_valid, error_msg = validator.validate_header_footer_params(
section_type, header_footer_type
)
if not is_valid:
return f"Error: {error_msg}"
is_valid, error_msg = validator.validate_text_content(content)
if not is_valid:
return f"Error: {error_msg}"
# Use HeaderFooterManager to handle the complex logic
header_footer_manager = HeaderFooterManager(service)
success, message = await header_footer_manager.update_header_footer_content(
document_id, section_type, content, header_footer_type
)
if success:
link = f"https://docs.google.com/document/d/{document_id}/edit"
return f"{message}. Runtime: {HEADER_FOOTER_RUNTIME_CANARY}. Link: {link}"
else:
return f"Error: {message}. Runtime: {HEADER_FOOTER_RUNTIME_CANARY}"
@server.tool()
@handle_http_errors("batch_update_doc", service_type="docs")
@require_google_service("docs", "docs_write")
async def batch_update_doc(
service: Any,
user_google_email: str,
document_id: str,
operations: BatchDocOperations,
) -> str:
"""
Executes multiple low-level document operations in a single atomic batch update.
For normal header/footer text, prefer update_doc_headers_footers.
Only use create_header_footer here for advanced section-break layouts.
RECOMMENDED WORKFLOW FOR BUILDING DOCUMENTS:
=============================================
To avoid index calculation errors, build documents in phases:
PHASE 1 - INSERT ALL CONTENT (use end_of_segment=true, no index math):