github-backup 0.62.1__py3-none-any.whl → 0.64.0__py3-none-any.whl

github_backup/__init__.py

@@ -1 +1 @@
-__version__ = "0.62.1"
+__version__ = "0.64.0"

github_backup/cli.py

@@ -81,7 +81,7 @@ def main():
     repositories = retrieve_repositories(args, authenticated_user)
     repositories = filter_repositories(args, repositories)
     backup_repositories(args, output_directory, repositories)
-    backup_account(args, output_directory)
+    backup_account(args, output_directory, authenticated_user)
 
 
 if __name__ == "__main__":

github_backup/github_backup.py

@@ -12,11 +12,11 @@ import os
 import platform
 import random
 import re
-import select
 import socket
 import ssl
 import subprocess
 import sys
+import threading
 import time
 from collections.abc import Generator
 from datetime import datetime
@@ -91,32 +91,37 @@ def logging_subprocess(
     child = subprocess.Popen(
         popenargs, stdout=subprocess.PIPE, stderr=subprocess.PIPE, **kwargs
     )
-    if sys.platform == "win32":
-        logger.info(
-            "Windows operating system detected - no subprocess logging will be returned"
-        )
-
-    log_level = {child.stdout: stdout_log_level, child.stderr: stderr_log_level}
-
-    def check_io():
-        if sys.platform == "win32":
-            return
-        ready_to_read = select.select([child.stdout, child.stderr], [], [], 1000)[0]
-        for io in ready_to_read:
-            line = io.readline()
-            if not logger:
-                continue
-            if not (io == child.stderr and not line):
-                logger.log(log_level[io], line[:-1])
-
-    # keep checking stdout/stderr until the child exits
-    while child.poll() is None:
-        check_io()
 
-    check_io()  # check again to catch anything after the process exits
+    def log_output(pipe, log_level):
+        # Drain the pipe from a thread so the child never blocks on a full
+        # pipe buffer (issue #519), logging each line as it arrives.
+        with pipe:
+            for line in iter(pipe.readline, b""):
+                try:
+                    logger.log(log_level, line.rstrip(b"\r\n"))
+                except Exception:
+                    # Keep draining even if logging fails, or the child
+                    # blocks on a full pipe buffer again
+                    pass
+
+    threads = [
+        threading.Thread(
+            target=log_output, args=(child.stdout, stdout_log_level), daemon=True
+        ),
+        threading.Thread(
+            target=log_output, args=(child.stderr, stderr_log_level), daemon=True
+        ),
+    ]
+    for thread in threads:
+        thread.start()
 
     rc = child.wait()
 
+    # Timeout in case a grandchild inherited the pipe handles and keeps
+    # them open past the child's exit, which would delay EOF indefinitely
+    for thread in threads:
+        thread.join(timeout=60)
+
     if rc != 0:
         print("{} returned {}:".format(popenargs[0], rc), file=sys.stderr)
         print("\t", " ".join(popenargs), file=sys.stderr)
@@ -2657,10 +2662,20 @@ def backup_pulls(args, repo_cwd, repository, repos_template):
     def pull_is_due_for_repository_checkpoint(pull):
         return not repository_since or pull["updated_at"] > repository_since
 
-    if not args.include_pull_details:
-        pull_states = ["open", "closed"]
-        for pull_state in pull_states:
-            query_args["state"] = pull_state
+    try:
+        if not args.include_pull_details:
+            pull_states = ["open", "closed"]
+            for pull_state in pull_states:
+                query_args["state"] = pull_state
+                for pull in retrieve_data(
+                    args, _pulls_template, query_args=query_args, lazy=True
+                ):
+                    track_newest_pull_update(pull)
+                    if pulls_since and pull["updated_at"] <= pulls_since:
+                        break
+                    if not pulls_since or pull["updated_at"] > pulls_since:
+                        pulls[pull["number"]] = pull
+        else:
             for pull in retrieve_data(
                 args, _pulls_template, query_args=query_args, lazy=True
             ):
@@ -2669,22 +2684,29 @@ def backup_pulls(args, repo_cwd, repository, repos_template):
                     break
                 if not pulls_since or pull["updated_at"] > pulls_since:
                     pulls[pull["number"]] = pull
-    else:
-        for pull in retrieve_data(
-            args, _pulls_template, query_args=query_args, lazy=True
-        ):
-            track_newest_pull_update(pull)
-            if pulls_since and pull["updated_at"] <= pulls_since:
-                break
-            if not pulls_since or pull["updated_at"] > pulls_since:
-                if pull_is_due_for_repository_checkpoint(pull):
-                    pulls[pull["number"]] = retrieve_data(
-                        args,
-                        _pulls_template + "/{}".format(pull["number"]),
-                        paginated=False,
-                    )[0]
-                else:
-                    pulls[pull["number"]] = pull
+    except HTTPError as e:
+        # Repositories with pull requests disabled return HTTP 404 for the
+        # listing endpoint; treat that as "no pull requests" rather than a
+        # fatal error. retrieve_data is lazy here, so the 404 surfaces during
+        # iteration. Only the listing call is guarded — a 404 on an individual
+        # pull's detail fetch below is a different condition and must propagate.
+        if e.code == 404:
+            logger.info("Pull requests are disabled for this repository, skipping")
+            return
+        raise
+
+    if args.include_pull_details:
+        # Replace the summary payload with the full pull detail. Done outside
+        # the disabled-feature guard above so a 404 on a single pull (e.g. one
+        # deleted between listing and fetch) is not mistaken for the whole
+        # feature being disabled, which would discard every collected pull.
+        for number in list(pulls.keys()):
+            if pull_is_due_for_repository_checkpoint(pulls[number]):
+                pulls[number] = retrieve_data(
+                    args,
+                    _pulls_template + "/{}".format(number),
+                    paginated=False,
+                )[0]
 
     logger.info("Saving {0} pull requests to disk".format(len(list(pulls.keys()))))
     # Comments from pulls API are only _review_ comments
@@ -2813,8 +2835,8 @@ def backup_security_advisories(args, repo_cwd, repository, repos_template):
 
     try:
         _advisories = retrieve_data(args, template)
-    except Exception as e:
-        if "404" in str(e):
+    except HTTPError as e:
+        if e.code == 404:
             logger.info("Security advisories are not available for this repository, skipping")
             return
         raise
@@ -2861,8 +2883,8 @@ def backup_hooks(args, repo_cwd, repository, repos_template):
     template = "{0}/{1}/hooks".format(repos_template, repository["full_name"])
     try:
         _backup_data(args, "hooks", template, output_file, hook_cwd)
-    except Exception as e:
-        if "404" in str(e):
+    except HTTPError as e:
+        if e.code == 404:
             logger.info("Unable to read hooks, skipping")
         else:
             raise e
@@ -3046,8 +3068,10 @@ def fetch_repository(
                 logging_subprocess(git_command, cwd=local_dir)
 
 
-def backup_account(args, output_directory):
+def backup_account(args, output_directory, authenticated_user=None):
     account_cwd = os.path.join(output_directory, "account")
+    if authenticated_user is None:
+        authenticated_user = {"login": None}
 
     if args.include_starred or args.include_everything:
         output_file = "{0}/starred.json".format(account_cwd)
@@ -3057,11 +3081,25 @@ def backup_account(args, output_directory):
         _backup_data(args, "starred repositories", template, output_file, account_cwd)
 
     if args.include_watched or args.include_everything:
-        output_file = "{0}/watched.json".format(account_cwd)
-        template = "https://{0}/users/{1}/subscriptions".format(
-            get_github_api_host(args), args.user
-        )
-        _backup_data(args, "watched repositories", template, output_file, account_cwd)
+        # GitHub deprecated /users/{username}/subscriptions; watched
+        # repositories are only available for the authenticated user via
+        # /user/subscriptions.
+        if (
+            not authenticated_user.get("login")
+            or args.user.lower() != authenticated_user["login"].lower()
+        ):
+            logger.warning(
+                "Cannot retrieve watched repositories for '%s'. GitHub only allows access to the authenticated user's watched repositories.",
+                args.user,
+            )
+        else:
+            output_file = "{0}/watched.json".format(account_cwd)
+            template = "https://{0}/user/subscriptions".format(
+                get_github_api_host(args)
+            )
+            _backup_data(
+                args, "watched repositories", template, output_file, account_cwd
+            )
 
     if args.include_followers or args.include_everything:
         output_file = "{0}/followers.json".format(account_cwd)

{github_backup-0.62.1.dist-info → github_backup-0.64.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: github-backup
-Version: 0.62.1
+Version: 0.64.0
 Summary: backup a github user or organization
 Home-page: http://github.com/josegonzalez/python-github-backup
 Author: Jose Diaz-Gonzalez

github_backup-0.64.0.dist-info/RECORD

@@ -0,0 +1,12 @@
+github_backup/__init__.py,sha256=4aEOIqCiMfp1lfhnZ0isYinRITBjjNflprA4nXib3RQ,23
+github_backup/__main__.py,sha256=3yorCiC63maaxbjdtaeAs-G-yAAxKSO3mprhGfa1Fho,271
+github_backup/cli.py,sha256=JTiXPOvB8id8LopREOEd1W_FLvuf9SOZU5buMRPFd9U,2922
+github_backup/github_backup.py,sha256=S5uxqZsYMnOGBYuEX9Dy1sipyUDyaeU7qXoLjkz3nLk,116637
+github_backup/graphql_queries.py,sha256=QBIXcGzGunilMpHfL32cTO_AAzxuQD27QII1V9K_Yw4,4883
+github_backup-0.64.0.dist-info/licenses/LICENSE.txt,sha256=ML-pLyn1qtAKo_DHMcQ8-p7k3f8cp-IR-mf5B49R2rk,1085
+github_backup-0.64.0.dist-info/METADATA,sha256=XSm6FyyldS86S0nFxbOMcS1lNkP0vVb8nTNLAMdF0J4,32426
+github_backup-0.64.0.dist-info/WHEEL,sha256=K260EYznzXsJYBQGqmI8VTxEdiZYNvDZwW9cBh9-_MA,91
+github_backup-0.64.0.dist-info/entry_points.txt,sha256=cLPKK7MqC77QVb6HnT2mnyL_f-ciavJG_Y9vVHlCF68,57
+github_backup-0.64.0.dist-info/top_level.txt,sha256=Za6fKRAlxZ0b3ZBH_osPqklLe14LetdNAkvAQANT2AA,14
+github_backup-0.64.0.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+github_backup-0.64.0.dist-info/RECORD,,

{github_backup-0.62.1.dist-info → github_backup-0.64.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (82.0.1)
+Generator: setuptools (83.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

github_backup-0.62.1.dist-info/RECORD

@@ -1,12 +0,0 @@
-github_backup/__init__.py,sha256=jT5y_EapSG_XUwBZcJ6_jD1uAUUE11ZbHJwMsKfUuQM,23
-github_backup/__main__.py,sha256=3yorCiC63maaxbjdtaeAs-G-yAAxKSO3mprhGfa1Fho,271
-github_backup/cli.py,sha256=gPYU0CviuHB19y8RHhcD0p8xHS3UcJbBIK6HVfWazTc,2902
-github_backup/github_backup.py,sha256=KIYfHJxxQn82C2K8RaAl4wmOSClxQWoBW8kFyFZ8pUw,114736
-github_backup/graphql_queries.py,sha256=QBIXcGzGunilMpHfL32cTO_AAzxuQD27QII1V9K_Yw4,4883
-github_backup-0.62.1.dist-info/licenses/LICENSE.txt,sha256=ML-pLyn1qtAKo_DHMcQ8-p7k3f8cp-IR-mf5B49R2rk,1085
-github_backup-0.62.1.dist-info/METADATA,sha256=5WD559hLSwkWmjiAtOFqZnyv-ycErCS7z1LUSAkdqRs,32426
-github_backup-0.62.1.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-github_backup-0.62.1.dist-info/entry_points.txt,sha256=cLPKK7MqC77QVb6HnT2mnyL_f-ciavJG_Y9vVHlCF68,57
-github_backup-0.62.1.dist-info/top_level.txt,sha256=Za6fKRAlxZ0b3ZBH_osPqklLe14LetdNAkvAQANT2AA,14
-github_backup-0.62.1.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-github_backup-0.62.1.dist-info/RECORD,,