Fix device type inference and add computer category

docs/device-mapper.md

@@ -25,7 +25,7 @@ python3 tools/device_mapper.py find --name 'L55M5-AD' --brand Xiaomi
   - `brand`: normalized brand
   - `manufacturer_brand`: manufacturer-level brand
   - `market_brand`: market sub-brand
-  - `device_type`: `phone | tablet | wear | tv | other`
+  - `device_type`: `phone | tablet | wear | tv | computer | other`
   - `aliases`: all searchable aliases
 - `lookup`: normalized alias -> candidate `record.id[]`
 - `brand_aliases`: normalized brand aliases to filter by app-provided brand
@@ -54,4 +54,5 @@ Supported categories:
 - `tablet`
 - `wear`
 - `tv`
+- `computer`
 - `other`

sql/mobilemodels_mysql_schema.sql

@@ -23,6 +23,36 @@ DEALLOCATE PREPARE stmt;
 
 USE `mobilemodels`;
 
+SET @drop_stmt = (
+  SELECT CASE `TABLE_TYPE`
+    WHEN 'BASE TABLE' THEN 'DROP TABLE `mm_device_catalog`'
+    WHEN 'VIEW' THEN 'DROP VIEW `mm_device_catalog`'
+    ELSE 'DO 0'
+  END
+  FROM `information_schema`.`TABLES`
+  WHERE `TABLE_SCHEMA` = 'mobilemodels' AND `TABLE_NAME` = 'mm_device_catalog'
+  LIMIT 1
+);
+SET @drop_stmt = COALESCE(@drop_stmt, 'DO 0');
+PREPARE stmt FROM @drop_stmt;
+EXECUTE stmt;
+DEALLOCATE PREPARE stmt;
+
+SET @drop_stmt = (
+  SELECT CASE `TABLE_TYPE`
+    WHEN 'BASE TABLE' THEN 'DROP TABLE `mm_brand_lookup`'
+    WHEN 'VIEW' THEN 'DROP VIEW `mm_brand_lookup`'
+    ELSE 'DO 0'
+  END
+  FROM `information_schema`.`TABLES`
+  WHERE `TABLE_SCHEMA` = 'mobilemodels' AND `TABLE_NAME` = 'mm_brand_lookup'
+  LIMIT 1
+);
+SET @drop_stmt = COALESCE(@drop_stmt, 'DO 0');
+PREPARE stmt FROM @drop_stmt;
+EXECUTE stmt;
+DEALLOCATE PREPARE stmt;
+
 SET @drop_stmt = (
   SELECT CASE `TABLE_TYPE`
     WHEN 'BASE TABLE' THEN 'DROP TABLE `mm_device_record`'
@@ -107,7 +137,7 @@ CREATE TABLE IF NOT EXISTS `mm_device_catalog` (
   `manufacturer_brand` varchar(64) NOT NULL,
   `parent_brand` varchar(64) NOT NULL,
   `market_brand` varchar(64) NOT NULL,
-  `device_type` enum('phone','tablet','wear','tv','other') NOT NULL,
+  `device_type` enum('phone','tablet','wear','tv','computer','other') NOT NULL,
   `code` varchar(64) DEFAULT NULL,
   `code_alias` varchar(255) DEFAULT NULL,
   `ver_name` text DEFAULT NULL,

tools/device_mapper.py

@@ -177,11 +177,17 @@ WEAR_KEYWORDS = [
     "glasses",
     "眼镜",
 ]
-OTHER_KEYWORDS = [
+COMPUTER_KEYWORDS = [
     "matebook",
+    "macbook",
     "笔记本",
+    "电脑",
     "laptop",
     "notebook",
+    "desktop",
+    "workstation",
+]
+OTHER_KEYWORDS = [
     "vision",
     "vr",
     "ipod",
@@ -248,9 +254,12 @@ def brand_aliases(brand: str) -> List[str]:
 
 
 def has_keyword(text: str, keywords: Iterable[str]) -> bool:
-    norm_text = normalize_text(text)
+    norm_text = re.sub(r"[^0-9a-z\u4e00-\u9fff]+", " ", text.lower())
+    norm_text = " ".join(norm_text.split())
     for kw in keywords:
-        if normalize_text(kw) and normalize_text(kw) in norm_text:
+        kw_norm = re.sub(r"[^0-9a-z\u4e00-\u9fff]+", " ", kw.lower())
+        kw_norm = " ".join(kw_norm.split())
+        if kw_norm and kw_norm in norm_text:
             return True
     return False
 
@@ -300,6 +309,8 @@ def infer_device_type(
         return "tablet"
     if has_keyword(corpus, WEAR_KEYWORDS):
         return "wear"
+    if has_keyword(corpus, COMPUTER_KEYWORDS):
+        return "computer"
     if has_keyword(corpus, OTHER_KEYWORDS):
         return "other"
     if has_keyword(corpus, PHONE_KEYWORDS):
@@ -385,6 +396,7 @@ def parse_brand_file(path: Path) -> List[DeviceRecord]:
 
         section_match = SECTION_RE.match(line)
         if section_match:
+            flush_current()
             section = section_match.group(1).strip()
             continue