refactor: 清理冗余代码和过时配置

This commit is contained in:
2026-06-14 12:56:02 +08:00
parent 90fe705e8f
commit 8f13c31991
8 changed files with 4 additions and 220 deletions
-1
View File
@@ -22,7 +22,6 @@ class Settings(BaseSettings):
# HuggingFace / arXiv
HF_API_BASE: str = "https://huggingface.co/api"
HF_PROXY: str = ""
TOP_N: int = 20
HTTP_TIMEOUT_SECONDS: int = 30
HTTP_MAX_RETRIES: int = 3
-4
View File
@@ -501,10 +501,6 @@ def _image_sort_key(name: str) -> tuple[int, int]:
m = re.search(r"(?:figure|table)_(\d+)", name)
if m:
return (0, int(m.group(1)))
# 旧格式:page2_img1.png, page5_table1.png, figure_1.png
m2 = re.search(r"page(\d+)_(?:img|table)(\d+)", name)
if m2:
return (int(m2.group(1)), int(m2.group(2)))
return (0, 0)
-15
View File
@@ -13,11 +13,8 @@ from pathlib import Path
from app.config import settings
from app.utils import truncate_error
from app.services.summary_utils import (
JsonNotFoundError,
build_prompt,
extract_json,
extract_pdf_text,
write_meta_json,
)
logger = logging.getLogger(__name__)
@@ -25,18 +22,6 @@ logger = logging.getLogger(__name__)
# PDF 全文注入模式的字符上限 — 超过此阈值自动切换到 search 模式
_PDF_MAX_CHARS = 80_000
# 重新导出,保持向后兼容
__all__ = [
"PiTimeoutError",
"PiProcessError",
"JsonNotFoundError",
"call_pi",
"write_meta_json",
"extract_pdf_text",
"build_prompt",
"extract_json",
]
# ── 自定义异常 ──────────────────────────────────────────────────────────
-16
View File
@@ -24,22 +24,6 @@ from app.utils import TMP_DIR, truncate_error, utc_now
logger = logging.getLogger(__name__)
# ── FTS5 文本构建 ───────────────────────────────────────────────────────
def _build_fts_summary_text(schema: SummarySchema) -> str:
"""拼接用于 FTS5 索引的总结文本。"""
parts = [
schema.one_line or "",
schema.motivation.problem or "",
schema.motivation.goal or "",
schema.method.overview or "",
schema.method.key_idea or "",
schema.results.main_findings or "",
]
return " ".join(p for p in parts if p)
# ── DB 更新 ─────────────────────────────────────────────────────────────