feat: implement search equivalence of "jpg" and "jpeg" filetypes (#649)

* feat: implement search equivalence of "jpg" and "jpeg" filetypes in an extensible manner

* docs: update completion for search features on roadmap

* fix: move FILETYPE_EQUIVALENTS to media_types.py

Author: Computerdores

docs/updates/roadmap.md

@@ -86,13 +86,13 @@ Features are broken up into the following priority levels, with nested prioritie
     -   [ ] GPS Location [LOW]
     -   [ ] Custom field names [HIGH] [#18](https://github.com/TagStudioDev/TagStudio/issues/18)
 -   [ ] Search engine [HIGH] [#325](https://github.com/TagStudioDev/TagStudio/issues/325)
-    -   [ ] Boolean operators [HIGH] [#225](https://github.com/TagStudioDev/TagStudio/issues/225), [#314](https://github.com/TagStudioDev/TagStudio/issues/314)
+    -   [x] Boolean operators [HIGH] [#225](https://github.com/TagStudioDev/TagStudio/issues/225), [#314](https://github.com/TagStudioDev/TagStudio/issues/314)
     -   [ ] Tag objects + autocomplete [HIGH] [#476 (Autocomplete)](https://github.com/TagStudioDev/TagStudio/issues/476)
-    -   [ ] Filename search [HIGH]
-    -   [ ] Filetype search [HIGH]
-        -   [ ] Search by extension (e.g. ".jpg", ".png") [HIGH]
-            -   [ ] Optional consolidation of extension synonyms (i.e. ".jpg" can equal ".jpeg") [LOW]
-        -   [ ] Search by media type (e.g. "image", "video", "document") [MEDIUM]
+    -   [x] Filename search [HIGH]
+    -   [x] Filetype search [HIGH]
+        -   [x] Search by extension (e.g. ".jpg", ".png") [HIGH]
+            -   [x] Optional consolidation of extension synonyms (i.e. ".jpg" can equal ".jpeg") [LOW]
+        -   [x] Search by media type (e.g. "image", "video", "document") [MEDIUM]
     -   [ ] Field content search [HIGH] [#272](https://github.com/TagStudioDev/TagStudio/issues/272)
     -   [ ] HAS operator for composition tags [HIGH]
     -   [ ] OCR search [LOW]
@@ -172,12 +172,12 @@ These version milestones are rough estimations for when the previous core featur
     -   [ ] [Tag Categories](../library/tag_categories.md) [HIGH]
         -   [ ] Property available for tags that allow the tag and any inheriting from it to be displayed separately in the preview panel under a title [HIGH]
 -   [ ] Search engine [HIGH]
-    -   [ ] Boolean operators [HIGH]
+    -   [x] Boolean operators [HIGH]
     -   [ ] Tag objects + autocomplete [HIGH]
     -   [x] Filename search [HIGH]
     -   [x] Filetype search [HIGH]
         -   [x] Search by extension (e.g. ".jpg", ".png") [HIGH]
-            -   [ ] Optional consolidation of extension synonyms (i.e. ".jpg" can equal ".jpeg") [LOW]
+            -   [x] Optional consolidation of extension synonyms (i.e. ".jpg" can equal ".jpeg") [LOW]
         -   [x] Search by media type (e.g. "image", "video", "document") [MEDIUM]
     -   [ ] Field content search [HIGH]
     -   [ ] Sortable results [HIGH]

tagstudio/src/core/library/alchemy/visitors.py

@@ -3,7 +3,7 @@
 from sqlalchemy import and_, distinct, func, or_, select
 from sqlalchemy.orm import Session
 from sqlalchemy.sql.expression import BinaryExpression, ColumnExpressionArgument
-from src.core.media_types import MediaCategories
+from src.core.media_types import FILETYPE_EQUIVALENTS, MediaCategories
 from src.core.query_lang import BaseVisitor
 from src.core.query_lang.ast import AST, ANDList, Constraint, ConstraintType, Not, ORList, Property
 
@@ -17,6 +17,13 @@
     Library = None  # don't import .library because of circular imports
 
 
+def get_filetype_equivalency_list(item: str) -> list[str] | set[str]:
+    for s in FILETYPE_EQUIVALENTS:
+        if item in s:
+            return s
+    return [item]
+
+
 class SQLBoolExpressionBuilder(BaseVisitor[ColumnExpressionArgument]):
     def __init__(self, lib: Library) -> None:
         super().__init__()
@@ -73,7 +80,9 @@ def visit_constraint(self, node: Constraint) -> ColumnExpressionArgument:
                     break
             return Entry.suffix.in_(map(lambda x: x.replace(".", ""), extensions))
         elif node.type == ConstraintType.FileType:
-            return Entry.suffix.ilike(node.value)
+            return or_(
+                *[Entry.suffix.ilike(ft) for ft in get_filetype_equivalency_list(node.value)]
+            )
         elif node.type == ConstraintType.Special:  # noqa: SIM102 unnecessary once there is a second special constraint
             if node.value.lower() == "untagged":
                 return ~Entry.id.in_(

tagstudio/src/core/media_types.py

@@ -10,6 +10,8 @@
 
 logging.basicConfig(format="%(message)s", level=logging.INFO)
 
+FILETYPE_EQUIVALENTS = [set(["jpg", "jpeg"])]
+
 
 class MediaType(str, Enum):
     """Names of media types."""