From bdbd7cf006410b37fc524ec62eb694092bc47f90 Mon Sep 17 00:00:00 2001
From: Steven Silvester <steven.silvester@ieee.org>
Date: Wed, 31 Jan 2024 16:18:42 -0600
Subject: [PATCH] update script to handle all path types

---
 scripts/migrate_to_md.py                      | 67 ++++++++++---------
 .../client-side-encryption/tests/README.rst   |  2 +-
 .../tests/cmap-format/README.md               | 10 +--
 .../tests/README.rst                          |  2 +-
 source/retryable-reads/retryable-reads.rst    |  2 +-
 source/retryable-writes/retryable-writes.rst  |  2 +-
 .../server-discovery-and-monitoring.rst       |  4 +-
 source/server-selection/server-selection.rst  |  2 +-
 8 files changed, 46 insertions(+), 45 deletions(-)

diff --git a/scripts/migrate_to_md.py b/scripts/migrate_to_md.py
index f47d177c39..63219f177d 100644
--- a/scripts/migrate_to_md.py
+++ b/scripts/migrate_to_md.py
@@ -84,54 +84,55 @@
 
 # Write the new content to the markdown file.
 md_file = str(path).replace('.rst', '.md')
-with open(md_file, 'w') as fid:
-    fid.write('\n'.join(new_lines))
+# with open(md_file, 'w') as fid:
+#     fid.write('\n'.join(new_lines))
 
 # Handle links in other files.
 # We accept relative path links or links to master 
 # (https://github.com/mongodb/specifications/blob/master/source/...)
 # and rewrite them to use appropriate md links.
 # If the link is malformed we ignore and print an error.
-curr = path
-target = path.name
-while curr.parent.name != "source":
-    target = f"{curr.parent.name}/{target}"
-    curr = curr.parent
-pattern = re.compile(f'(<.*{target}[>#])')
-pattern2 = re.compile(f'(/source/{target}[>#])')
-for p in Path("source").rglob("*.rst"):
+rel_pattern = re.compile(f'(\.\.\S*/{path.name})')
+md_pattern = re.compile(f'(\(http\S*/{path.name})')
+rst_pattern = re.compile(f'(<http\S*/{path.name})')
+abs_pattern = re.compile(f'(/source/\S*/{path.name})')
+for p in Path("source").rglob("*"):
+    if p.suffix not in ['.rst', '.md']:
+        continue
     found = False
     with p.open() as fid:
         lines = fid.readlines()
     new_lines = []
+    relpath = os.path.relpath(md_file, start=p.parent)
     for line in lines:
-        match = re.search(pattern, line)
-        if not match:
-            match = re.search(pattern2, line)
-            if match:
-                found = True
-                new_name = path.name.replace('.rst', '.md')
-                line = line.replace(path.name, new_name)
-            new_lines.append(line)
-            continue
-        matchstr = match.groups()[0]
-        if matchstr[0].startswith('https'):
-            substr = match.string
-            if not substr.startswith('<https://github.com/mongodb/specifications/blob/master/source/'):
-                print('*** Error in link: ', substr, p)
-                new_lines.append(line)
-                continue
-        found = True
-        relpath = os.path.relpath(path.parent.parent, start=p.parent)
-        new_name = path.name.replace('.rst', '.md')
-        new_substr = f'<{relpath}/{path.parent.name}/{new_name}{matchstr[-1]}'
-        new_lines.append(line.replace(matchstr, new_substr))
+        new_line = line
+        if re.search(rel_pattern, line):
+            matchstr = re.search(rel_pattern, line).groups()[0]
+            new_line = line.replace(matchstr, relpath)
+        elif re.search(md_pattern, line):
+            matchstr = re.search(md_pattern, line).groups()[0]
+            if not matchstr.startswith('(https://github.com/mongodb/specifications/blob/master/source'):
+                print('*** Error in link: ', matchstr, p)
+            else:
+                new_line = line.replace(matchstr, f'({relpath}')
+        elif re.search(rst_pattern, line):
+            matchstr = re.search(rst_pattern, line).groups()[0]
+            if not matchstr.startswith('<https://github.com/mongodb/specifications/blob/master/source'):
+                print('*** Error in link: ', matchstr, p)
+            else:
+                new_line = line.replace(matchstr, f'<{relpath}')
+        elif re.search(abs_pattern, line):
+            matchstr = re.search(abs_pattern, line).groups()[0]
+            new_line = line.replace(matchstr, relpath)
+
+        if new_line != line:
+            found = True
+        new_lines.append(new_line)
 
     if found:
         with p.open('w') as fid:
             fid.writelines(new_lines)
-        print(f'Update link(s) in {p.name}')
-
+        print(f'Update link(s) in {p}')
 
 
 print('Created markdown file:')
diff --git a/source/client-side-encryption/tests/README.rst b/source/client-side-encryption/tests/README.rst
index 52554f6743..935b824a4e 100644
--- a/source/client-side-encryption/tests/README.rst
+++ b/source/client-side-encryption/tests/README.rst
@@ -1125,7 +1125,7 @@ Repeat the steps from the "Via bypassAutoEncryption" test, replacing "bypassAuto
 9. Deadlock Tests
 ~~~~~~~~~~~~~~~~~
 
-.. _Connection Monitoring and Pooling: /source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst
+.. _Connection Monitoring and Pooling: ../../connection-monitoring-and-pooling/connection-monitoring-and-pooling.md
 
 The following tests only apply to drivers that have implemented a connection pool (see the `Connection Monitoring and Pooling`_ specification).
 
diff --git a/source/connection-monitoring-and-pooling/tests/cmap-format/README.md b/source/connection-monitoring-and-pooling/tests/cmap-format/README.md
index b925c0aa19..50d12f3458 100644
--- a/source/connection-monitoring-and-pooling/tests/cmap-format/README.md
+++ b/source/connection-monitoring-and-pooling/tests/cmap-format/README.md
@@ -22,12 +22,12 @@ Each YAML file has the following keys:
 All Unit Tests have some of the following fields:
 
 - `poolOptions`: If present, connection pool options to use when creating a pool; both
-  [standard ConnectionPoolOptions](https://github.com/mongodb/specifications/blob/master/source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst#connection-pool-options-1)
-  and the following test-specific options are allowed:
+  [standard ConnectionPoolOptions](../../connection-monitoring-and-pooling.md#connection-pool-options-1) and the
+  following test-specific options are allowed:
   - `backgroundThreadIntervalMS`: A time interval between the end of a
-    [Background Thread Run](https://github.com/mongodb/specifications/blob/master/source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst#background-thread)
-    and the beginning of the next Run. If a Connection Pool does not implement a Background Thread, the Test Runner MUST
-    ignore the option. If the option is not specified, an implementation is free to use any value it finds reasonable.
+    [Background Thread Run](../../connection-monitoring-and-pooling.md#background-thread) and the beginning of the next
+    Run. If a Connection Pool does not implement a Background Thread, the Test Runner MUST ignore the option. If the
+    option is not specified, an implementation is free to use any value it finds reasonable.
 
     Possible values (0 is not allowed):
 
diff --git a/source/connections-survive-step-down/tests/README.rst b/source/connections-survive-step-down/tests/README.rst
index 0ffbf3dd17..de52113939 100644
--- a/source/connections-survive-step-down/tests/README.rst
+++ b/source/connections-survive-step-down/tests/README.rst
@@ -172,7 +172,7 @@ methodology is in contrast to the one adopted by the SDAM spec tests that rely e
 server communication.
 
 
-.. _CMAP: /source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst
+.. _CMAP: ../../connection-monitoring-and-pooling/connection-monitoring-and-pooling.md
 .. _PoolClearedEvent: /source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.md#events
 .. _serverStatus: https://www.mongodb.com/docs/manual/reference/command/serverStatus
 .. _connections.totalCreated: https://www.mongodb.com/docs/manual/reference/command/serverStatus/#serverstatus.connections.totalCreated
diff --git a/source/retryable-reads/retryable-reads.rst b/source/retryable-reads/retryable-reads.rst
index 7238d87ba7..43eefd6966 100644
--- a/source/retryable-reads/retryable-reads.rst
+++ b/source/retryable-reads/retryable-reads.rst
@@ -71,7 +71,7 @@ SocketException                    9001
 
 - a `PoolClearedError`_
 
-  .. _PoolClearedError: ../connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst#connection-pool-errors
+  .. _PoolClearedError: ../connection-monitoring-and-pooling/connection-monitoring-and-pooling.md#connection-pool-errors
 
 - Any of the above retryable errors that occur during a connection handshake (including the
   authentication step). For example, a network error or ShutdownInProgress error
diff --git a/source/retryable-writes/retryable-writes.rst b/source/retryable-writes/retryable-writes.rst
index 4ba39c2218..6bdc2a6a65 100644
--- a/source/retryable-writes/retryable-writes.rst
+++ b/source/retryable-writes/retryable-writes.rst
@@ -238,7 +238,7 @@ The RetryableWriteError label might be added to an error in a variety of ways:
   the MongoClient performing the operation has the retryWrites configuration
   option set to true.
 
-  .. _PoolClearedError: ../connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst#connection-pool-errors
+  .. _PoolClearedError: ../connection-monitoring-and-pooling/connection-monitoring-and-pooling.md#connection-pool-errors
 
 - For server versions 4.4 and newer, the server will add a RetryableWriteError
   label to errors or server responses that it considers retryable before
diff --git a/source/server-discovery-and-monitoring/server-discovery-and-monitoring.rst b/source/server-discovery-and-monitoring/server-discovery-and-monitoring.rst
index 19f3769e25..e349fabeb2 100644
--- a/source/server-discovery-and-monitoring/server-discovery-and-monitoring.rst
+++ b/source/server-discovery-and-monitoring/server-discovery-and-monitoring.rst
@@ -2557,7 +2557,7 @@ Changelog
 .. _scanning order: server-monitoring.rst#scanning-order
 .. _clients update the topology from each handshake: server-monitoring.rst#clients-update-the-topology-from-each-handshake
 .. _single-threaded monitoring: server-monitoring.rst#single-threaded-monitoring
-.. _Connection Monitoring and Pooling spec: /source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst
-.. _CMAP spec: /source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst
+.. _Connection Monitoring and Pooling spec: ../connection-monitoring-and-pooling/connection-monitoring-and-pooling.md
+.. _CMAP spec: ../connection-monitoring-and-pooling/connection-monitoring-and-pooling.md
 .. _Authentication spec: /source/auth/auth.rst
 .. _Server Monitoring (Measuring RTT): server-monitoring.rst#measuring-rtt
diff --git a/source/server-selection/server-selection.rst b/source/server-selection/server-selection.rst
index c57c1c39f5..fb7d185ded 100644
--- a/source/server-selection/server-selection.rst
+++ b/source/server-selection/server-selection.rst
@@ -2024,7 +2024,7 @@ References
 .. _idleWritePeriodMS: https://github.com/mongodb/specifications/blob/master/source/max-staleness/max-staleness.rst#idlewriteperiodms
 .. _Driver Authentication: https://github.com/mongodb/specifications/blob/master/source/auth
 .. _maxConnecting: /source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.md#connection-pool
-.. _Connection Monitoring and Pooling: /source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst
+.. _Connection Monitoring and Pooling: ../connection-monitoring-and-pooling/connection-monitoring-and-pooling.md
 .. _Global Command Argument: /source/message/OP_MSG.rst#global-command-arguments
 
 Changelog