From 5e22d1d9a63f821ef2b2d35026f8bb9d41aee943 Mon Sep 17 00:00:00 2001
From: Victor <annimon119@gmail.com>
Date: Wed, 14 Apr 2021 23:59:28 +0300
Subject: [PATCH] Sanitize character tags by removing copyright suffix

---
 _README.md  |  3 +++
 library.py  | 11 +++--------
 metadata.py |  2 +-
 tags.py     | 18 ++++++++++++++++++
 4 files changed, 25 insertions(+), 9 deletions(-)
 create mode 100644 _README.md

diff --git a/_README.md b/_README.md
new file mode 100644
index 0000000..06b84df
--- /dev/null
+++ b/_README.md
@@ -0,0 +1,3 @@
+## PicSorter
+
+Finds an image on danbooru, writes tags as IPTC keywords, than places the image in the library
\ No newline at end of file
diff --git a/library.py b/library.py
index d2068c9..8f34d7c 100644
--- a/library.py
+++ b/library.py
@@ -7,7 +7,7 @@ import os
 class Library:
     def __init__(self, dir_root: Path):
         self.dir_root = dir_root
-        self.dir_orphan = Path(dir_root, 'orphan')
+        self.dir_orphan = Path(dir_root, '_orphan')
         self.dir_orphan.mkdir(exist_ok=True, parents=True)
     
     def move_to_orphan(self, p: Path):
@@ -37,14 +37,9 @@ class Library:
         if tags.characters == "":
             return p
         # Characters section
-        characters = tags.characters.split(" ")
+        characters = tags.characters_sanitized()
         if len(characters) == 1:
-            character = characters[0] \
-                .replace(copyright, "") \
-                .replace("("+copyright+")", "") \
-                .replace("()", "") \
-                .strip()
-            p = p / self.__sanitize(character)
+            p = p / self.__sanitize(characters[0])
         else:
             p = p / "_multiple"
         return p
diff --git a/metadata.py b/metadata.py
index cdb516b..cbbac06 100644
--- a/metadata.py
+++ b/metadata.py
@@ -91,7 +91,7 @@ class Metadata:
     def __format_filename(self, tags: Tags):
         filename = '{} {} by {} at {}.jpg'.format(
             tags.copyrights.split(" ")[0] or "",
-            ", ".join(tags.characters.split(" ")[:2]),
+            ", ".join(tags.characters_sanitized()[:2]),
             tags.artists.split(" ")[0] or "",
             datetime.now().strftime('%Y%m%d_%H%M%S')
         )
diff --git a/tags.py b/tags.py
index 40f3d5e..619858c 100644
--- a/tags.py
+++ b/tags.py
@@ -14,6 +14,24 @@ class Tags:
         self.tags = self.__union_tags()
         self.tags_string = " ".join(self.tags)
     
+    def characters_sanitized(self) -> list:
+        if self.copyrights == "":
+            # No need to sanitize tags
+            return self.characters.split(" ")
+        copyrights = self.copyrights.split(" ")
+        return _(self.characters) \
+                .split(" ") \
+                .filter(lambda s: s != "") \
+                .map(lambda s: self.__rename(s, copyrights)) \
+                ._
+    
+    def __rename(self, s: str, substrings: list) -> str:
+        for substring in substrings:
+            s = s.replace("_("+substring+")", "") \
+                .replace("("+substring+")", "") \
+                .strip()
+        return s
+
     def __union_tags(self):
         tags = self.general.split(" ")
         tags += self.__prefix_tags(self.copyrights, 'copyright_')