| """Shared parsing/masking helpers for the GSM8K reasoning dataset translation.""" |
| import re |
|
|
| RECORD_RE = re.compile( |
| r"<question>(.*?)</question>\s*<thinking>(.*?)</thinking>\s*<answer>(.*?)</answer>", re.S |
| ) |
| NUM_RE = re.compile(r"\d+(?:\.\d+)?") |
| PH_RE = re.compile(r"#(\d+)#") |
|
|
| SRC_PROMPT = "Translate the following English sentence into Arabic:\n{text} <ar>" |
|
|
|
|
| def parse(text): |
| m = RECORD_RE.match(text.strip()) |
| if not m: |
| return None |
| return m.group(1).strip(), m.group(2).strip(), m.group(3).strip() |
|
|
|
|
| def mask_numbers(text): |
| """'168 + 19 = 187' -> ('#0# + #1# = #2#', ['168', '19', '187'])""" |
| nums = [] |
|
|
| def repl(m): |
| nums.append(m.group(0)) |
| return f"#{len(nums) - 1}#" |
|
|
| return NUM_RE.sub(repl, text), nums |
|
|
|
|
| def unmask_numbers(text, nums): |
| """Restore. Returns (text, ok) — ok is False if any placeholder was lost or duplicated.""" |
| seen = [] |
|
|
| def repl(m): |
| i = int(m.group(1)) |
| seen.append(i) |
| return nums[i] if i < len(nums) else m.group(0) |
|
|
| out = PH_RE.sub(repl, text) |
| return out, sorted(seen) == list(range(len(nums))) |
|
|
|
|
| def build_record(question, thinking, answer): |
| return f"<question>{question}</question> <thinking>{thinking}</thinking> <answer>{answer}</answer>" |
|
|
