Merge remote-tracking branch 'upstream/master'

TOC.md

@@ -1062,6 +1062,7 @@
   - v7.6
     - [7.6.0-DMR](/releases/release-7.6.0.md)
   - v7.5
+    - [7.5.2](/releases/release-7.5.2.md)
     - [7.5.1](/releases/release-7.5.1.md)
     - [7.5.0](/releases/release-7.5.0.md)
   - v7.4

releases/release-notes.md

@@ -22,6 +22,7 @@ summary: TiDB has released multiple versions, including 8.1.0, 8.0.0-DMR, 7.6.0-
 
 ## 7.5
 
+- [7.5.2](/releases/release-7.5.2.md): 2024-06-13
 - [7.5.1](/releases/release-7.5.1.md): 2024-02-29
 - [7.5.0](/releases/release-7.5.0.md): 2023-12-01
 

releases/release-timeline.md

@@ -11,6 +11,7 @@ This document shows all the released TiDB versions in reverse chronological orde
 
 | Version | Release Date |
 | :--- | :--- |
+| [7.5.2](/releases/release-7.5.2.md) | 2024-06-13 |
 | [8.1.0](/releases/release-8.1.0.md) | 2024-05-24 |
 | [7.1.5](/releases/release-7.1.5.md) | 2024-04-26 |
 | [6.5.9](/releases/release-6.5.9.md) | 2024-04-12 |

scripts/release_notes_update_pr_author_info_add_dup.py

@@ -10,6 +10,7 @@
 from github import Github
 import re
 import openpyxl
+from openpyxl.styles import PatternFill
 import os
 import shutil
 import requests
@@ -26,7 +27,7 @@
 def store_exst_rn(ext_path, version):
 
     exst_notes = []
-    exst_issue_nums = []
+    exst_issue_nums_and_authors = []
     exst_note_levels = []
     release_file = os.path.join(ext_path, f'release-{version}.md')
 
@@ -43,10 +44,11 @@ def store_exst_rn(ext_path, version):
                         exst_issue_num = re.search(r'https://github.com/(pingcap|tikv)/[\w-]+/(issues|pull)/\d+', line)
                         authors = re.findall(r'@\[([^\]]+)\]', line) # Get the list of authors in this line
                         if exst_issue_num:
-                            if exst_issue_num.group() not in exst_issue_nums:
+                            exst_issue_num_and_author = [exst_issue_num.group(), authors]
+                            if exst_issue_num_and_author not in exst_issue_nums_and_authors:
                                 note_level = level1 + level2 + level3
                                 note_pair = [exst_issue_num.group(),line.strip(),afile, note_level, authors]
-                                exst_issue_nums.append(exst_issue_num.group())
+                                exst_issue_nums_and_authors.append(exst_issue_num_and_author)
                                 exst_notes.append(note_pair)
                             else:
                                 continue
@@ -63,7 +65,7 @@ def store_exst_rn(ext_path, version):
             else:
                 pass
 
-    if len(exst_issue_nums) != 0:
+    if len(exst_issue_nums_and_authors) != 0:
         return exst_notes
     else:
         return 0
@@ -128,6 +130,7 @@ def update_pr_author_and_release_notes(excel_path):
     # Go through each row
     dup_notes = []
     dup_notes_levels = []
+    grey_fill = PatternFill(start_color="D3D3D3", end_color="D3D3D3", fill_type="solid")
     for row_index, row in enumerate(sheet.iter_rows(min_row=2, values_only=True), start=2):
         # If pr_author is ti-chi-bot or ti-srebot
         current_pr_author = row[pr_author_index]
@@ -144,14 +147,17 @@ def update_pr_author_and_release_notes(excel_path):
             pass
 
         ## Add the dup release note info
-        issue_link = re.search('https://github.com/(pingcap|tikv)/[\w-]+/issues/\d+', current_formated_rn)
+        issue_link = re.search(r'https://github.com/(pingcap|tikv)/[\w-]+/issues/\d+', current_formated_rn)
         if issue_link:
             for note_pair in note_pairs:
                 if (issue_link.group() == note_pair[0]) and ((current_pr_author in note_pair[4]) or len(note_pair[4]) == 0): # Add the dup release notes only if the issues link is the same as the existing one and the current author is in the existing author list
                     #print('A duplicated note is found in row ' + str(row_index) + " from " + note_pair[2] + note_pair[1])
                     dup_formated_rn = '- (dup): {} {} {}'.format(note_pair[2], note_pair[3], note_pair[1])
                     #print (note_pair)
                     sheet.cell(row=row_index, column=pr_last_col_index+1, value=dup_formated_rn)
+                    # Apply the grey color to the row with dup note
+                    for column in range(1, pr_last_col_index + 2):
+                        sheet.cell(row=row_index, column=column).fill = grey_fill
                     if dup_formated_rn not in dup_notes: # Collect the dup release note if it is not collected before
                         dup_notes.append(dup_formated_rn)
                         print ("-----")

ticdc/ticdc-changefeed-config.md

@@ -128,7 +128,7 @@ enable-table-across-nodes = false
 # For example, if you specify the routing rule for a matcher as the string `code`, then all Pulsar messages that match that matcher will be routed with `code` as the key.
 # dispatchers = [
 #    {matcher = ['test1.*', 'test2.*'], topic = "Topic expression 1", partition = "index-value"},
-#    {matcher = ['test3.*', 'test4.*'], topic = "Topic expression 2", partition = "index-value", index-name="index1"},
+#    {matcher = ['test3.*', 'test4.*'], topic = "Topic expression 2", partition = "index-value", index = "index1"},
 #    {matcher = ['test1.*', 'test5.*'], topic = "Topic expression 3", partition = "table"},
 #    {matcher = ['test6.*'], partition = "columns", columns = "['a', 'b']"}
 #    {matcher = ['test7.*'], partition = "ts"}

ticdc/ticdc-sink-to-kafka.md

@@ -255,7 +255,7 @@ For example, for a dispatcher like `matcher = ['test.*'], topic = {schema}_{tabl
 You can use `partition = "xxx"` to specify a partition dispatcher. It supports five dispatchers: `default`, `index-value`, `columns`, `table`, and `ts`. The dispatcher rules are as follows:
 
 - `default`: uses the `table` dispatcher rule by default. It calculates the partition number using the schema name and table name, ensuring data from a table is sent to the same partition. As a result, the data from a single table only exists in one partition and is guaranteed to be ordered. However, this dispatcher rule limits the send throughput, and the consumption speed cannot be improved by adding consumers.
-- `index-value`: calculates the partition number using either the primary key, a unique index, or an explicitly specified index, distributing table data across multiple partitions. The data from a single table is sent to multiple partitions, and the data in each partition is ordered. You can improve the consumption speed by adding consumers.
+- `index-value`: calculates the partition number using either the primary key, a unique index, or an index explicitly specified by `index`, distributing table data across multiple partitions. The data from a single table is sent to multiple partitions, and the data in each partition is ordered. You can improve the consumption speed by adding consumers.
 - `columns`: calculates the partition number using the values of explicitly specified columns, distributing table data across multiple partitions. The data from a single table is sent to multiple partitions, and the data in each partition is ordered. You can improve the consumption speed by adding consumers.
 - `table`: calculates the partition number using the schema name and table name.
 - `ts`: calculates the partition number using the commitTs of the row change, distributing table data across multiple partitions. The data from a single table is sent to multiple partitions, and the data in each partition is ordered. You can improve the consumption speed by adding consumers. However, multiple changes of a data item might be sent to different partitions and the consumer progress of different consumers might be different, which might cause data inconsistency. Therefore, the consumer needs to sort the data from multiple partitions by commitTs before consuming.
@@ -266,14 +266,14 @@ Take the following configuration of `dispatchers` as an example:
 [sink]
 dispatchers = [
     {matcher = ['test.*'], partition = "index-value"},
-    {matcher = ['test1.*'], partition = "index-value", index-name = "index1"},
+    {matcher = ['test1.*'], partition = "index-value", index = "index1"},
     {matcher = ['test2.*'], partition = "columns", columns = ["id", "a"]},
     {matcher = ['test3.*'], partition = "table"},
 ]
 ```
 
 - Tables in the `test` database use the `index-value` dispatcher, which calculates the partition number using the value of the primary key or unique index. If a primary key exists, the primary key is used; otherwise, the shortest unique index is used.
-- Tables in the `test1` table use the `index-value` dispatcher and calculate the partition number using values of all columns in the index named `index1`. If the specified index does not exist, an error is reported. Note that the index specified by `index-name` must be a unique index.
+- Tables in the `test1` table use the `index-value` dispatcher and calculate the partition number using values of all columns in the index named `index1`. If the specified index does not exist, an error is reported. Note that the index specified by `index` must be a unique index.
 - Tables in the `test2` database use the `columns` dispatcher and calculate the partition number using the values of columns `id` and `a`. If any of the columns does not exist, an error is reported.
 - Tables in the `test3` database use the `table` dispatcher.
 - Tables in the `test4` database use the `default` dispatcher, that is the `table` dispatcher, as they do not match any of the preceding rules.