X-Git-Url: https://git.immae.eu/?a=blobdiff_plain;f=tap_google_sheets%2Fstreams.py;h=ad5529f4ac3defef3ae215cfb7c1cf701e98137c;hb=0a0f2e89de6cde25ba6ef104c64e30f92091e007;hp=231a41d0cde60e8915136e7f79bbf44b1454201d;hpb=66bc495f76684fc0de611643e7c464bd46203125;p=github%2Ffretlink%2Ftap-google-sheets.git

diff --git a/tap_google_sheets/streams.py b/tap_google_sheets/streams.py
index 231a41d..ad5529f 100644
--- a/tap_google_sheets/streams.py
+++ b/tap_google_sheets/streams.py
@@ -8,12 +8,13 @@ from collections import OrderedDict
 #   key_properties: Primary key fields for identifying an endpoint record.
 #   replication_method: INCREMENTAL or FULL_TABLE
 #   replication_keys: bookmark_field(s), typically a date-time, used for filtering the results
-#        and setting the state
+#       and setting the state
 #   params: Query, sort, and other endpoint specific parameters; default = {}
-#   data_key: JSON element containing the results list for the endpoint; default = root (no data_key)
-#   bookmark_query_field: From date-time field used for filtering the query
-#   bookmark_type: Data type for bookmark, integer or datetime
+#   data_key: JSON element containing the results list for the endpoint;
+#       default = root (no data_key)
 
+# file_metadata: Queries Google Drive API to get file information and see if file has been modified
+#    Provides audit info about who and when last changed the file.
 FILE_METADATA = {
     "api": "files",
     "path": "files/{spreadsheet_id}",
@@ -25,6 +26,7 @@ FILE_METADATA = {
     }
 }
 
+# spreadsheet_metadata: Queries spreadsheet to get basic information on spreadhsheet and sheets
 SPREADSHEET_METADATA = {
     "api": "sheets",
     "path": "spreadsheets/{spreadsheet_id}",
@@ -35,6 +37,9 @@ SPREADSHEET_METADATA = {
     }
 }
 
+# sheet_metadata: Get Header Row and 1st data row (Rows 1 & 2) from a Sheet on Spreadsheet.
+# This endpoint includes detailed metadata about each cell in the header and first data row
+#   incl. data type, formatting, etc.
 SHEET_METADATA = {
     "api": "sheets",
     "path": "spreadsheets/{spreadsheet_id}",
@@ -46,6 +51,8 @@ SHEET_METADATA = {
     }
 }
 
+# sheets_loaded: Queries a batch of Rows for each Sheet in the Spreadsheet.
+# Each query uses the `values` endpoint, to get data-only, w/out the formatting/type metadata.
 SHEETS_LOADED = {
     "api": "sheets",
     "path": "spreadsheets/{spreadsheet_id}/values/'{sheet_title}'!{range_rows}",
@@ -59,7 +66,7 @@ SHEETS_LOADED = {
     }
 }
 
-# Ensure streams are ordered logically
+# Ensure streams are ordered sequentially, logically.
 STREAMS = OrderedDict()
 STREAMS['file_metadata'] = FILE_METADATA
 STREAMS['spreadsheet_metadata'] = SPREADSHEET_METADATA