init
This commit is contained in:
wanhae.lee
+215
@@ -0,0 +1,215 @@
|
||||
"""Minimal Gemma4 tool-call parser.
|
||||
|
||||
Pure-function port of sglang's Gemma4Detector parsing helpers
|
||||
(sglang/python/sglang/srt/function_call/gemma4_detector.py), so generated
|
||||
outputs can be validated exactly the way sglang would parse them, without
|
||||
importing sglang.
|
||||
"""
|
||||
|
||||
TOOL_CALL_START = "<|tool_call>"
|
||||
TOOL_CALL_END = "<tool_call|>"
|
||||
STRING_DELIM = '<|"|>'
|
||||
|
||||
|
||||
def _parse_value(value_str: str) -> object:
|
||||
value_str = value_str.strip()
|
||||
if not value_str:
|
||||
return value_str
|
||||
if value_str == "true":
|
||||
return True
|
||||
if value_str == "false":
|
||||
return False
|
||||
try:
|
||||
if "." in value_str:
|
||||
return float(value_str)
|
||||
return int(value_str)
|
||||
except ValueError:
|
||||
pass
|
||||
return value_str
|
||||
|
||||
|
||||
def _parse_array(arr_str: str) -> list:
|
||||
items: list = []
|
||||
i = 0
|
||||
n = len(arr_str)
|
||||
while i < n:
|
||||
while i < n and arr_str[i] in (" ", ",", "\n", "\t"):
|
||||
i += 1
|
||||
if i >= n:
|
||||
break
|
||||
if arr_str[i : i + len(STRING_DELIM)] == STRING_DELIM:
|
||||
i += len(STRING_DELIM)
|
||||
end_pos = arr_str.find(STRING_DELIM, i)
|
||||
if end_pos == -1:
|
||||
items.append(arr_str[i:])
|
||||
break
|
||||
items.append(arr_str[i:end_pos])
|
||||
i = end_pos + len(STRING_DELIM)
|
||||
elif arr_str[i] == "{":
|
||||
depth = 1
|
||||
obj_start = i + 1
|
||||
i += 1
|
||||
while i < n and depth > 0:
|
||||
if arr_str[i : i + len(STRING_DELIM)] == STRING_DELIM:
|
||||
i += len(STRING_DELIM)
|
||||
next_delim = arr_str.find(STRING_DELIM, i)
|
||||
i = next_delim + len(STRING_DELIM) if next_delim != -1 else n
|
||||
continue
|
||||
if arr_str[i] == "{":
|
||||
depth += 1
|
||||
elif arr_str[i] == "}":
|
||||
depth -= 1
|
||||
i += 1
|
||||
items.append(parse_args(arr_str[obj_start : i - 1]))
|
||||
elif arr_str[i] == "[":
|
||||
depth = 1
|
||||
sub_start = i + 1
|
||||
i += 1
|
||||
while i < n and depth > 0:
|
||||
if arr_str[i] == "[":
|
||||
depth += 1
|
||||
elif arr_str[i] == "]":
|
||||
depth -= 1
|
||||
i += 1
|
||||
items.append(_parse_array(arr_str[sub_start : i - 1]))
|
||||
else:
|
||||
val_start = i
|
||||
while i < n and arr_str[i] not in (",", "]"):
|
||||
i += 1
|
||||
items.append(_parse_value(arr_str[val_start:i]))
|
||||
return items
|
||||
|
||||
|
||||
def parse_args(args_str: str) -> dict:
|
||||
"""Parse Gemma4's key:value argument format into a Python dict."""
|
||||
if not args_str or not args_str.strip():
|
||||
return {}
|
||||
result: dict = {}
|
||||
i = 0
|
||||
n = len(args_str)
|
||||
while i < n:
|
||||
while i < n and args_str[i] in (" ", ",", "\n", "\t"):
|
||||
i += 1
|
||||
if i >= n:
|
||||
break
|
||||
key_start = i
|
||||
while i < n and args_str[i] != ":":
|
||||
i += 1
|
||||
if i >= n:
|
||||
break
|
||||
key = args_str[key_start:i].strip()
|
||||
i += 1
|
||||
if i >= n:
|
||||
result[key] = ""
|
||||
break
|
||||
while i < n and args_str[i] in (" ", "\n", "\t"):
|
||||
i += 1
|
||||
if i >= n:
|
||||
result[key] = ""
|
||||
break
|
||||
if args_str[i : i + len(STRING_DELIM)] == STRING_DELIM:
|
||||
i += len(STRING_DELIM)
|
||||
val_start = i
|
||||
end_pos = args_str.find(STRING_DELIM, i)
|
||||
if end_pos == -1:
|
||||
result[key] = args_str[val_start:]
|
||||
break
|
||||
result[key] = args_str[val_start:end_pos]
|
||||
i = end_pos + len(STRING_DELIM)
|
||||
elif args_str[i] == "{":
|
||||
depth = 1
|
||||
obj_start = i + 1
|
||||
i += 1
|
||||
while i < n and depth > 0:
|
||||
if args_str[i : i + len(STRING_DELIM)] == STRING_DELIM:
|
||||
i += len(STRING_DELIM)
|
||||
next_delim = args_str.find(STRING_DELIM, i)
|
||||
i = n if next_delim == -1 else next_delim + len(STRING_DELIM)
|
||||
continue
|
||||
if args_str[i] == "{":
|
||||
depth += 1
|
||||
elif args_str[i] == "}":
|
||||
depth -= 1
|
||||
i += 1
|
||||
result[key] = parse_args(args_str[obj_start : i - 1])
|
||||
elif args_str[i] == "[":
|
||||
depth = 1
|
||||
arr_start = i + 1
|
||||
i += 1
|
||||
while i < n and depth > 0:
|
||||
if args_str[i : i + len(STRING_DELIM)] == STRING_DELIM:
|
||||
i += len(STRING_DELIM)
|
||||
next_delim = args_str.find(STRING_DELIM, i)
|
||||
i = n if next_delim == -1 else next_delim + len(STRING_DELIM)
|
||||
continue
|
||||
if args_str[i] == "[":
|
||||
depth += 1
|
||||
elif args_str[i] == "]":
|
||||
depth -= 1
|
||||
i += 1
|
||||
result[key] = _parse_array(args_str[arr_start : i - 1])
|
||||
else:
|
||||
val_start = i
|
||||
while i < n and args_str[i] not in (",", "}", "]"):
|
||||
i += 1
|
||||
result[key] = _parse_value(args_str[val_start:i])
|
||||
return result
|
||||
|
||||
|
||||
def _find_matching_brace(text: str) -> int:
|
||||
"""Index of the matching '}' in text (which starts just after '{'), or -1."""
|
||||
depth = 1
|
||||
i = 0
|
||||
n = len(text)
|
||||
dlen = len(STRING_DELIM)
|
||||
while i < n and depth > 0:
|
||||
if text[i : i + dlen] == STRING_DELIM:
|
||||
i += dlen
|
||||
next_delim = text.find(STRING_DELIM, i)
|
||||
if next_delim == -1:
|
||||
return -1
|
||||
i = next_delim + dlen
|
||||
continue
|
||||
if text[i] == "{":
|
||||
depth += 1
|
||||
elif text[i] == "}":
|
||||
depth -= 1
|
||||
i += 1
|
||||
return (i - 1) if depth == 0 else -1
|
||||
|
||||
|
||||
def extract_tool_calls(text: str) -> list:
|
||||
"""Extract [(func_name, args_dict_or_None)] from text.
|
||||
|
||||
args is None when the call block is malformed (unparseable), mirroring
|
||||
where sglang's detector would fail.
|
||||
"""
|
||||
results = []
|
||||
search_from = 0
|
||||
while True:
|
||||
start = text.find(TOOL_CALL_START, search_from)
|
||||
if start == -1:
|
||||
break
|
||||
end = text.find(TOOL_CALL_END, start)
|
||||
if end == -1:
|
||||
# unterminated call block
|
||||
results.append((None, None))
|
||||
break
|
||||
inner = text[start + len(TOOL_CALL_START) : end]
|
||||
if inner.startswith("call:"):
|
||||
brace = inner.find("{")
|
||||
if brace != -1:
|
||||
func_name = inner[5:brace]
|
||||
args_content = inner[brace + 1 :]
|
||||
match_idx = _find_matching_brace(args_content)
|
||||
args_str = args_content[:match_idx] if match_idx != -1 else args_content
|
||||
try:
|
||||
results.append((func_name, parse_args(args_str)))
|
||||
except Exception:
|
||||
results.append((func_name, None))
|
||||
else:
|
||||
results.append((None, None))
|
||||
else:
|
||||
results.append((None, None))
|
||||
search_from = end + len(TOOL_CALL_END)
|
||||
return results
|
||||
Reference in New Issue
Block a user