arcade-google-docs 4.3.2__py3-none-any.whl → 5.0.1__py3-none-any.whl

arcade_google_docs/utils.py

@@ -4,7 +4,11 @@ from typing import Any
 from google.oauth2.credentials import Credentials
 from googleapiclient.discovery import Resource, build
 
-from arcade_google_docs.enum import Corpora, OrderBy
+from arcade_google_docs.doc_to_html import convert_document_to_html
+from arcade_google_docs.doc_to_markdown import convert_document_to_markdown
+from arcade_google_docs.docmd import build_docmd
+from arcade_google_docs.enum import Corpora, DocumentFormat, OrderBy
+from arcade_google_docs.models.document import StructuralElement
 
 ## Set up basic configuration for logging to the console with DEBUG level and a specific format.
 logging.basicConfig(
@@ -20,7 +24,7 @@ def build_docs_service(auth_token: str | None) -> Resource:  # type: ignore[no-a
     Build a Drive service object.
     """
     auth_token = auth_token or ""
-    return build("docs", "v1", credentials=Credentials(auth_token))
+    return build("docs", "v1", credentials=Credentials(auth_token), cache_discovery=False)
 
 
 def build_drive_service(auth_token: str | None) -> Resource:  # type: ignore[no-any-unimported]
@@ -28,7 +32,7 @@ def build_drive_service(auth_token: str | None) -> Resource:  # type: ignore[no-
     Build a Drive service object.
     """
     auth_token = auth_token or ""
-    return build("drive", "v3", credentials=Credentials(auth_token))
+    return build("drive", "v3", credentials=Credentials(auth_token), cache_discovery=False)
 
 
 def build_files_list_params(
@@ -117,3 +121,260 @@ def remove_none_values(params: dict) -> dict:
     :return: A new dictionary with None values removed
     """
     return {k: v for k, v in params.items() if v is not None}
+
+
+def build_tab_metadata_recursive(
+    tabs: list, max_depth: int = 4, current_depth: int = 0
+) -> list[Any]:
+    """Build hierarchical tab metadata preserving nested structure.
+
+    Args:
+        tabs: List of Tab objects with potential childTabs
+        max_depth: Maximum recursion depth (Google Docs enforces 3 levels, using 4 for safety)
+        current_depth: Current recursion depth
+
+    Returns:
+        List of TabMetadata dicts with nested childTabs
+    """
+    if current_depth >= max_depth:
+        return []
+
+    result: list[Any] = []
+
+    for tab in tabs:
+        if not tab.tabProperties:
+            continue
+
+        char_count = 0
+        word_count = 0
+        if tab.documentTab and tab.documentTab.body:
+            char_count = _calculate_character_count(tab.documentTab.body.content)
+            word_count = _calculate_word_count(tab.documentTab.body.content)
+
+        nesting_level = tab.tabProperties.nestingLevel or 0
+        if not isinstance(nesting_level, int) or nesting_level < 0:
+            nesting_level = 0
+
+        tab_meta_dict: dict = {
+            "tabId": tab.tabProperties.tabId or "",
+            "title": tab.tabProperties.title or "",
+            "index": tab.tabProperties.index or 0,
+            "nestingLevel": nesting_level,
+            "approximateCharacterCount": char_count,
+            "approximateWordCount": word_count,
+        }
+
+        if tab.tabProperties.parentTabId:
+            tab_meta_dict["parentTabId"] = tab.tabProperties.parentTabId
+
+        if tab.childTabs and current_depth < max_depth - 1:
+            tab_meta_dict["childTabs"] = build_tab_metadata_recursive(
+                tab.childTabs, max_depth, current_depth + 1
+            )
+
+        result.append(tab_meta_dict)
+
+    return result
+
+
+def count_tab_chars_recursive(tab_meta: dict) -> int:
+    """Recursively count characters in a tab and its children.
+
+    Args:
+        tab_meta: TabMetadata dict potentially with childTabs
+
+    Returns:
+        Total character count including all descendants
+    """
+    count: int = tab_meta.get("approximateCharacterCount", 0)
+    if "childTabs" in tab_meta:
+        count += sum(count_tab_chars_recursive(child) for child in tab_meta["childTabs"])
+    return count
+
+
+def count_tab_words_recursive(tab_meta: dict) -> int:
+    """Recursively count words in a tab and its children.
+
+    Args:
+        tab_meta: TabMetadata dict potentially with childTabs
+
+    Returns:
+        Total word count including all descendants
+    """
+    count: int = tab_meta.get("approximateWordCount", 0)
+    if "childTabs" in tab_meta:
+        count += sum(count_tab_words_recursive(child) for child in tab_meta["childTabs"])
+    return count
+
+
+def _calculate_character_count(content: list[StructuralElement] | None) -> int:
+    """Calculate total character count from body content.
+
+    Args:
+        content: List of structural elements from a body
+
+    Returns:
+        Total number of characters in the content
+    """
+    if not content:
+        return 0
+
+    char_count = 0
+    for element in content:
+        if element.paragraph:
+            for el in element.paragraph.elements or []:
+                if el.textRun and el.textRun.content:
+                    char_count += len(el.textRun.content)
+        elif element.table:
+            for row in element.table.tableRows or []:
+                for cell in row.tableCells or []:
+                    char_count += _calculate_character_count(cell.content)
+
+    return char_count
+
+
+def _calculate_word_count(content: list[StructuralElement] | None) -> int:
+    """Calculate total word count from body content.
+
+    Args:
+        content: List of structural elements from a body
+
+    Returns:
+        Total number of words in the content
+    """
+    if not content:
+        return 0
+
+    word_count = 0
+    for element in content:
+        if element.paragraph:
+            for el in element.paragraph.elements or []:
+                if el.textRun and el.textRun.content:
+                    text = el.textRun.content.strip()
+                    if text:
+                        word_count += len(text.split())
+        elif element.table:
+            for row in element.table.tableRows or []:
+                for cell in row.tableCells or []:
+                    word_count += _calculate_word_count(cell.content)
+
+    return word_count
+
+
+def calculate_total_tabs_characters(tabs: list, max_depth: int = 4, current_depth: int = 0) -> int:
+    """Calculate total character count from all tabs recursively.
+
+    Args:
+        tabs: List of Tab objects
+        max_depth: Maximum recursion depth (Google Docs enforces 3 levels, using 4 for safety)
+        current_depth: Current recursion depth
+
+    Returns:
+        Total character count across all tabs
+    """
+    if current_depth >= max_depth:
+        return 0
+
+    total = 0
+    for tab in tabs:
+        if tab.documentTab and tab.documentTab.body:
+            total += _calculate_character_count(tab.documentTab.body.content)
+        if tab.childTabs:
+            total += calculate_total_tabs_characters(tab.childTabs, max_depth, current_depth + 1)
+    return total
+
+
+def calculate_total_tabs_words(tabs: list, max_depth: int = 4, current_depth: int = 0) -> int:
+    """Calculate total word count from all tabs recursively.
+
+    Args:
+        tabs: List of Tab objects
+        max_depth: Maximum recursion depth (Google Docs enforces 3 levels, using 4 for safety)
+        current_depth: Current recursion depth
+
+    Returns:
+        Total word count across all tabs
+    """
+    if current_depth >= max_depth:
+        return 0
+
+    total = 0
+    for tab in tabs:
+        if tab.documentTab and tab.documentTab.body:
+            total += _calculate_word_count(tab.documentTab.body.content)
+        if tab.childTabs:
+            total += calculate_total_tabs_words(tab.childTabs, max_depth, current_depth + 1)
+    return total
+
+
+def build_document_content_result(document: Any, doc_dict: dict, return_format: Any) -> dict:
+    """Build a DocumentContentResult from a document.
+
+    Args:
+        document: Parsed Document object
+        doc_dict: Raw document dict for conversion functions
+        return_format: Desired output format (DocumentFormat enum)
+
+    Returns:
+        DocumentContentResult with content and metadata
+    """
+    tabs_count = len(document.tabs) if document.tabs else 0
+
+    total_char_count = 0
+    total_word_count = 0
+    main_body_char_count = 0
+    main_body_word_count = 0
+
+    if document.tabs and len(document.tabs) > 0:
+        total_char_count = calculate_total_tabs_characters(document.tabs)
+        total_word_count = calculate_total_tabs_words(document.tabs)
+
+    if document.body:
+        main_body_char_count = _calculate_character_count(document.body.content)
+        main_body_word_count = _calculate_word_count(document.body.content)
+        if tabs_count == 0:
+            total_char_count = main_body_char_count
+            total_word_count = main_body_word_count
+
+    content: str
+    if return_format == DocumentFormat.DOCMD:
+        content = build_docmd(document).to_string()
+    elif return_format == DocumentFormat.MARKDOWN:
+        content = convert_document_to_markdown(doc_dict, include_all_tabs=True)
+    else:
+        content = convert_document_to_html(doc_dict, include_all_tabs=True)
+
+    return {
+        "documentId": document.documentId or "",
+        "title": document.title or "",
+        "documentUrl": f"https://docs.google.com/document/d/{document.documentId}/edit",
+        "content": content,
+        "format": return_format.value,
+        "tabs_count": tabs_count,
+        "total_character_count": total_char_count,
+        "total_word_count": total_word_count,
+        "main_body_character_count": main_body_char_count,
+        "main_body_word_count": main_body_word_count,
+    }
+
+
+def build_search_retrieve_response(documents: list[dict], search_response: dict) -> dict:
+    """Build final response for search and retrieve operation.
+
+    Args:
+        documents: List of processed documents with content
+        search_response: Response from search_documents
+
+    Returns:
+        Complete search and retrieve response
+    """
+    result_dict: dict = {
+        "documents_count": len(documents),
+        "documents": documents,
+        "has_more": search_response["has_more"],
+    }
+
+    if "pagination_token" in search_response:
+        result_dict["pagination_token"] = search_response["pagination_token"]
+
+    return result_dict

arcade_google_docs/who_am_i_util.py

@@ -74,7 +74,7 @@ def _extract_google_docs_info(docs_service: Any) -> dict[str, Any]:
 
 def _build_people_service(credentials: Credentials) -> Any:
     """Build and return the People API service client."""
-    return build("people", "v1", credentials=credentials)
+    return build("people", "v1", credentials=credentials, cache_discovery=False)
 
 
 def _get_people_api_data(people_service: Any) -> dict[str, Any]:

{arcade_google_docs-4.3.2.dist-info → arcade_google_docs-5.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arcade_google_docs
-Version: 4.3.2
+Version: 5.0.1
 Summary: Arcade.dev LLM tools for Google Docs
 Author-email: Arcade <dev@arcade.dev>
 License: Proprietary - Arcade Software License Agreement v1.0

{arcade_google_docs-4.3.2.dist-info → arcade_google_docs-5.0.1.dist-info}/RECORD

@@ -1,20 +1,21 @@
-arcade_google_docs/__init__.py,sha256=nZoMwH9HWZLpfNMIioUXLDlZ7QDR-E4C1_8hySt_CkU,604
-arcade_google_docs/doc_to_html.py,sha256=6RTpzRSrazNa6AndLZhA20wgVDzZuHUqpu3WAkAsbjQ,3146
-arcade_google_docs/doc_to_markdown.py,sha256=eT-sc6ruxN8nEtUm9mBHFOWXajEBTTXkxsn6XsLHIxo,2020
-arcade_google_docs/docmd.py,sha256=rgxUt0k2Nes0GWLlPR49qU0nnM8e6HCiqd61Z7zNfTk,20173
+arcade_google_docs/__init__.py,sha256=IjNb08C6cdnCIQDsBGj1_t_FlNizeBqkyhNiOrfZiMY,746
+arcade_google_docs/doc_to_html.py,sha256=qD2QR17J4EOPsQYaNVdfHJl4rPISytOw3QaocOxs4g4,7836
+arcade_google_docs/doc_to_markdown.py,sha256=Hq651d2nk48rO7piGncSPZx4KFEGVu-mBQ6kFJUGi8w,6295
+arcade_google_docs/docmd.py,sha256=Dw8ZAgR_9Df9nKoJSvmslU4fbUtCuteW5bfmyXytwnU,23324
 arcade_google_docs/enum.py,sha256=kuXlsHcMYbN28Qg-Dwp4viz-CZ8z85_WVjQVZj2EsEY,3441
 arcade_google_docs/templates.py,sha256=pxbdMj57eV3-ImW3CixDWscpVKS94Z8nTNyTxDhUfGY,283
-arcade_google_docs/utils.py,sha256=XMgKcWPWKy8SbH3y2eCil01hssHhUgYxVrwXyvHEU4A,3748
-arcade_google_docs/who_am_i_util.py,sha256=NGQpQ0CuE2N86mGpkIdujXBRjcPBJ5SJ9BYzlb3mGFI,2925
+arcade_google_docs/utils.py,sha256=lANqXh6rvKjGBcqFbs-_0cQsA80oHywey4ZKUBXQYYQ,12527
+arcade_google_docs/who_am_i_util.py,sha256=Atg64UcY3wrwKi71k9e33Stm70_xeCriwisTISb-GDk,2948
 arcade_google_docs/models/document.py,sha256=0RvZ2_dfpz6ZoF1aUucYWOkRYWy_K_hiChSzoQtwhTc,30419
 arcade_google_docs/models/document_writables.py,sha256=DMBT5A05y7o7_PYlBB6O3KThma6-pm6hd5nxKGydT5Q,27575
 arcade_google_docs/models/requests.py,sha256=8Cga7QECmQWNFhM2QiGudvnQcgA_THi7ThNsUb7uavg,52176
-arcade_google_docs/tools/__init__.py,sha256=kQChYFQ6y1LJg7q6fngzCOPtaDH1-CeWUOzqxfR_oGY,904
+arcade_google_docs/models/responses.py,sha256=82douA0aEvc90FzeYqnxzCB0MkhxqvrzBl_IbfIrPr0,4308
+arcade_google_docs/tools/__init__.py,sha256=JqdaeKJqlFI4cXWEOg960uQCeiIksdD0EDEEOcVu3_0,1025
 arcade_google_docs/tools/comment.py,sha256=Qm5NHdNHONs3j4gqbZ7Fw9NrTVBb_mZ-th1X-z2IoLM,2836
 arcade_google_docs/tools/create.py,sha256=AuYy8yMGscrxAdLJQX0WiisGHCTufSlaRu_QGMMKQmM,2764
 arcade_google_docs/tools/file_picker.py,sha256=Dqn-hfMoTsWyHM8QCakVgHr5TKrzL_1Lj-vYHVGtOW4,2342
-arcade_google_docs/tools/get.py,sha256=Aby3iI1EzjfZTovGH4OdwpIhuazfV4SQinpXDOl87cg,2076
-arcade_google_docs/tools/search.py,sha256=1k1cI-fKOo4SZU4ufCwZ4DysK3l9MhPScZggPfNCC5Y,8261
+arcade_google_docs/tools/get.py,sha256=VQpFxnposGMGS1ulw_3EurIsX3LLi8P3Qxz0X4a0vA0,4297
+arcade_google_docs/tools/search.py,sha256=H_u_zJhUIAwWAkn_iGqbjcnh8z5lWyGK480Y5RpsM1U,8286
 arcade_google_docs/tools/system_context.py,sha256=19HPSpNkLsb-MDWc-9CFgK_ha-rRzwaJr7hV6Us_1LI,1130
 arcade_google_docs/tools/update.py,sha256=_dReYit0s7ykn2bYQEUwohl3D_63U5leF87egO4eEiQ,1836
 arcade_google_docs/tools/edit_agent/edit_agent.py,sha256=1LIgKrQ70pDWzWNoaoy1st659perqa-ZW_ALmbVRbW0,2439
@@ -23,8 +24,8 @@ arcade_google_docs/tools/edit_agent/planner.py,sha256=38aslAnlPDEY3JEoVXtHqL3Oq_
 arcade_google_docs/tools/edit_agent/progress_tracker.py,sha256=eb69tk-yL3uhEEo4ggPoBFtZtHTA6OwgcPxELtvbeEs,1280
 arcade_google_docs/tools/edit_agent/prompts.py,sha256=M_f-HsPJppd3FQPhRAw7pKpaArkVfz213mKVx8qHp8A,15149
 arcade_google_docs/tools/edit_agent/request_generator.py,sha256=eVDmzJDsOmJ-S8yANmJATt_G51rgCcCga6ArX4DTShM,5399
-arcade_google_docs/tools/edit_agent/utils.py,sha256=6lYmdQfX4CHfemP5PfxcXKSYpbdqFyEad997-gzCD48,639
+arcade_google_docs/tools/edit_agent/utils.py,sha256=uAxhI43KALjDiD6yxlb8sLoPAV-oHKrF5jk2lgITPv0,680
 arcade_google_docs/tools/edit_agent/models/planning.py,sha256=RWQFB_KHl3Pq-snv1rHzoRxVvTnHVLZEGRpdohSX7wc,2962
-arcade_google_docs-4.3.2.dist-info/METADATA,sha256=TqCY7_7TrTWCr1vkq7h1iWQiotgOveAJ0SOYXtvGRTI,1128
-arcade_google_docs-4.3.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-arcade_google_docs-4.3.2.dist-info/RECORD,,
+arcade_google_docs-5.0.1.dist-info/METADATA,sha256=WoZXPsv3jEyVQW0aMD7WvG5Tu31RhZ74nPLqnL3eZ9Q,1128
+arcade_google_docs-5.0.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+arcade_google_docs-5.0.1.dist-info/RECORD,,

{arcade_google_docs-4.3.2.dist-info → arcade_google_docs-5.0.1.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.27.0
+Generator: hatchling 1.28.0
 Root-Is-Purelib: true
 Tag: py3-none-any