From 9e12e96d90a7c5b76544c8379b289510902469ec Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Julius=20R=C3=BCberg?=
 <22551563+Toorero@users.noreply.github.com>
Date: Tue, 2 Nov 2021 03:42:08 +0100
Subject: [PATCH] Added alias functionality

---
 CONFIG.md      |  4 ++++
 PFERD/pferd.py | 24 +++++++++++++++++++-----
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/CONFIG.md b/CONFIG.md
index 8ccaa50..0775eb1 100644
--- a/CONFIG.md
+++ b/CONFIG.md
@@ -86,6 +86,9 @@ common to all crawlers:
   load for the crawl target. (Default: `0.0`)
 - `windows_paths`: Whether PFERD should find alternative names for paths that
   are invalid on Windows. (Default: `yes` on Windows, `no` otherwise)
+- `alias`: List of strings that are considered as an alias when invoking with
+  the `--crawler` or `-C` flag. If there is more then one crawl section with
+  the same alias all are selected. Thereby you can group different crawlers.
 
 Some crawlers may also require credentials for authentication. To configure how
 the crawler obtains its credentials, the `auth` option is used. It is set to the
@@ -100,6 +103,7 @@ username = foo
 password = bar
 
 [crawl:something]
+alias = [sth, some]
 type = some-complex-crawler
 auth = auth:example
 on_conflict = no-delete
diff --git a/PFERD/pferd.py b/PFERD/pferd.py
index 726ed45..6ed31a0 100644
--- a/PFERD/pferd.py
+++ b/PFERD/pferd.py
@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Set
 
 from rich.markup import escape
 
@@ -43,16 +43,22 @@ class Pferd:
 
         crawl_sections = [name for name, _ in config.crawl_sections()]
 
-        crawlers_to_run = []  # With crawl: prefix
+        crawlers_to_run = set()  # With crawl: prefix
         unknown_names = []  # Without crawl: prefix
 
         for name in cli_crawlers:
             section_name = f"crawl:{name}"
             if section_name in crawl_sections:
                 log.explain(f"Crawler section named {section_name!r} exists")
-                crawlers_to_run.append(section_name)
-            else:
-                log.explain(f"There's no crawler section named {section_name!r}")
+                crawlers_to_run.add(section_name)
+            alias_names = self._find_crawlers_by_alias(name, config)
+            if alias_names:
+                crawlers_to_run.update(alias_names)
+                log.explain_topic(f"Crawler alias {name!r} found corresponding crawler sections:")
+                for alias_name in alias_names:
+                    log.explain(f"Crawler section named {alias_name!r} with alias {name!r} exists")
+            if not section_name in crawl_sections and not alias_names:
+                log.explain(f"There's neither a crawler section named {section_name!r} nor does a crawler with alias {name!r} exist.")
                 unknown_names.append(name)
 
         if unknown_names:
@@ -65,6 +71,14 @@ class Pferd:
 
         return crawlers_to_run
 
+    def _find_crawlers_by_alias(self, alias: str, config: Config) -> Set[str]:
+        alias_names = set()
+        for (section_name, section) in config.crawl_sections():
+            section_alias = section.get("alias", [])
+            if alias in section_alias:
+                alias_names.add(section_name)
+        return alias_names
+
     def _find_crawlers_to_run(
             self,
             config: Config,