diff options
| -rw-r--r-- | src/conventionalrp/core/parser.py | 50 | ||||
| -rw-r--r-- | test/example_rule.json | 94 |
2 files changed, 63 insertions, 81 deletions
diff --git a/src/conventionalrp/core/parser.py b/src/conventionalrp/core/parser.py index f451178..f214c4c 100644 --- a/src/conventionalrp/core/parser.py +++ b/src/conventionalrp/core/parser.py @@ -23,6 +23,7 @@ class Parser: # to be continue... self.rules = rules + print(f"Rules loaded: {rules}\n") def parse_log(self, log_path: str): """Parse the TRPG log based on loaded rules.""" @@ -45,39 +46,38 @@ class Parser: # metadata detect is_metadata = False - for rule in self.rules: - if rule.get("type") == "metadata": - patterns = rule.get("patterns", []) - for pattern in patterns: - match = re.search(pattern, line) - if match: - # If it's metadata, save the previous content - if current_metadata: - parsed_data.append({ - **current_metadata, - "content": current_content - }) - current_content = [] - - # Parsing new metadata - current_metadata = {} - groups = rule.get("groups", []) - for i, key in enumerate(groups): - if i + 1 <= len(match.groups()): # Ensure effective - current_metadata[key] = match.group(i + 1).strip() - is_metadata = True - break - if is_metadata: - break + metadata_content = self.rules.get("metadata") + patterns = metadata_content.get("patterns", []) + for pattern in patterns: + match = re.search(pattern, line) + if match: + # If it's metadata, save the previous content + if current_metadata: + parsed_data.append({ + **current_metadata, + "content": current_content + }) + current_content = [] + + # Parsing new metadata + current_metadata = {} + groups = metadata_content.get("groups", []) + for i, key in enumerate(groups): + if i + 1 <= len(match.groups()): # Ensure effective + current_metadata[key] = match.group(i + 1).strip() + is_metadata = True + break if is_metadata: continue # The metadata line has been processed, skip subsequent content matching # content detect remaining_line = line + rules = self.rules.get("content") while remaining_line: matched = False - for rule in self.rules: + + for rule in rules: # pass metadata rule if rule["type"] == "metadata": continue diff --git a/test/example_rule.json b/test/example_rule.json index 0cb5b6c..750789a 100644 --- a/test/example_rule.json +++ b/test/example_rule.json @@ -1,66 +1,48 @@ -[
+{
+ "metadata": {
+ // 匹配日志元数据，提取 id、QQ 账号和时间。例如：墨勒托.DW(1571806261) 2025-01-27 19:58:15
+ "type": "metadata",
+ "patterns": [
+ "^(\\S+)\\((\\d+)\\)\\s+(\\d{4}-\\d{2}-\\d{2} \\d{2}:\\d{2}:\\d{2})"
+ ],
+ "groups": ["user_name", "user_id", "time"]
+ },
+ "content": [
{
- // 匹配日志元数据，提取 id、QQ 账号和时间。例如：墨勒托.DW(1571806261) 2025-01-27 19:58:15
- "type": "metadata",
- "patterns": [
- "^(\\S+)\\((\\d+)\\)\\s+(\\d{4}-\\d{2}-\\d{2} \\d{2}:\\d{2}:\\d{2})"
- ],
- "groups": [
- "user_name",
- "user_id",
- "time"
- ]
+ "type": "action",
+ "patterns": ["^#s*((?:(?![“”\"（【】]).)+)"], // 排除后续特殊符号
+ "groups": ["action_content"]
},
{
- "type": "action",
- "patterns": [
- "^#s*((?:(?![“”\"（【】]).)+)"
- ], // 排除后续特殊符号
- "groups": [
- "action_content"
- ]
+ "type": "speech",
+ "patterns": [
+ "[“](.+?)[”]", // 中文引号
+ "\"(.*?)\"", // 英文引号
+ "”(.+?)“" // 混合引号
+ ],
+ "groups": ["speech_content"]
},
{
- "type": "speech",
- "patterns": [
- "[“](.+?)[”]", // 中文引号
- "\"(.*?)\"", // 英文引号
- "”(.+?)“" // 混合引号
- ],
- "groups": [
- "speech_content"
- ]
+ "type": "ooc_speech",
+ "patterns": [
+ // "((.*?))", // 英文括号
+ "（(.*?)）", // 中文括号
+ // "((.*)", // 未闭合英文括号
+ "（(.*)" // 未闭合中文括号
+ ],
+ "groups": ["ooc_content"]
},
{
- "type": "ooc_speech",
- "patterns": [
- // "((.*?))", // 英文括号
- "（(.*?)）", // 中文括号
- // "((.*)", // 未闭合英文括号
- "（(.*)" // 未闭合中文括号
- ],
- "groups": [
- "ooc_content"
- ]
+ // 匹配掷骰指令，以 . 或 。开头但是不匹配连续的指令前缀。例如：匹配".ra智力"，不匹配"。。。"
+ "type": "dice_order",
+ "patterns": ["^(?:[\\.。]([^.。].+))"],
+ "groups": ["dice_command"]
},
{
- // 匹配掷骰指令，以 . 或 。开头但是不匹配连续的指令前缀。例如：匹配".ra智力"，不匹配"。。。"
- "type": "dice_order",
- "patterns": [
- "^(?:[\\.。]([^.。].+))"
- ],
- "groups": [
- "dice_command"
- ]
- },
- {
- // 匹配角色心理活动。例如：【这里好可怕】
- "type": "thought",
- "patterns": [
- "【(.+)】"
- ],
- "groups": [
- "thought_content"
- ]
+ // 匹配角色心理活动。例如：【这里好可怕】
+ "type": "thought",
+ "patterns": ["【(.+)】"],
+ "groups": ["thought_content"]
}
-]
\ No newline at end of file + ]
+}
|