Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
09f681beb5 |
@@ -170,12 +170,13 @@ Follow `skill:humanizer-cn` §1-26 strictly:
|
||||
|
||||
## Hard Rules
|
||||
|
||||
1. ✅ Every claim has `[src_xxx]` citation
|
||||
2. ✅ Every numerical fact has a source
|
||||
3. ✅ Counter-evidence section is mandatory (not optional)
|
||||
4. ✅ Word count ≥85% of quota, or continue searching
|
||||
5. ✅ No scheduling metadata in body text (no "P0 core", "quota: X", "researcher: dr-analyst")
|
||||
6. ✅ No SCQA labels (not even implicitly suggested by structure)
|
||||
7. ❌ Never fabricate data, URLs, DOIs
|
||||
8. ❌ Never use Chinese words for claims (English working language)
|
||||
9. ❌ Never delegate to other agents
|
||||
1. MUST: Every claim has `[src_xxx]` citation
|
||||
2. MUST: Every numerical fact has a source
|
||||
3. MUST: Counter-evidence section is mandatory (not optional)
|
||||
4. MUST: Word count ≥85% of quota, or continue searching
|
||||
5. MUST: No scheduling metadata in body text (no "P0 core", "quota: X", "researcher: dr-analyst")
|
||||
6. MUST: No SCQA labels (not even implicitly suggested by structure)
|
||||
7. MUST NOT: Fabricate data, URLs, DOIs
|
||||
8. MUST NOT: Use Chinese words for claims (English working language)
|
||||
9. MUST NOT: Delegate to other agents
|
||||
10. MUST NOT: **Use emoji anywhere in the draft** (no ✅ ❌ 🔶 🔷 ⭐ 🟢 🔴 ⚠️ 💡 📌 🔑 📊 etc.). The PDF font has no glyphs for colored emoji; they render as empty boxes. Use plain text equivalents (e.g., "✓", "×", "注:", "警告:", or descriptive words like "advantages / limitations / example").
|
||||
|
||||
@@ -299,8 +299,9 @@ Phase 4 成稿完成
|
||||
|
||||
## 禁止事项
|
||||
|
||||
- ❌ 改写 dr-analyst 已完成的章节正文
|
||||
- ❌ 给每章开头强加 "**Situation**:" "**Complication**:" 等标注
|
||||
- ❌ 在正文里保留"章节定位 / P0 核心章 / 字数配额 / 研究员"
|
||||
- ❌ 参考文献用占位符了事,要确保 dr-reporter 把它填满
|
||||
- ❌ 中途调用 dr-chief-editor(它只管 Phase 3)
|
||||
- 改写 dr-analyst 已完成的章节正文
|
||||
- 给每章开头强加 "**Situation**:" "**Complication**:" 等标注
|
||||
- 在正文里保留"章节定位 / P0 核心章 / 字数配额 / 研究员"
|
||||
- 参考文献用占位符了事,要确保 dr-reporter 把它填满
|
||||
- 中途调用 dr-chief-editor(它只管 Phase 3)
|
||||
- **在正文中使用 emoji**(✅ ❌ 🔶 🔷 ⭐ 🟢 🔴 ⚠️ 💡 📌 🔑 📊 等彩色符号)。PDF 字体无法渲染,会变成方框。用文字或简单符号(✓ × 注: 警告:)代替。
|
||||
|
||||
@@ -101,6 +101,34 @@ SCQA 要写得隐式融合(见 mckinsey-method skill)。
|
||||
|
||||
例外:行内英文术语、代码、URL、数据单位前后保持英文标点合理。
|
||||
|
||||
### J. Emoji(强制禁用)
|
||||
|
||||
**正文与表格中严禁使用任何 emoji / 彩色符号**:
|
||||
|
||||
禁用清单(但不限于):
|
||||
`✅ ❌ ✔ ✖ 🔶 🔷 ⭐ 🟢 🔴 🟡 🟠 ⚠️ ⚠ 💡 📌 🔑 📊 📈 📉 🔥 ✨ 🎯 🎉 ➔ ➜`
|
||||
|
||||
**原因**:PDF 使用的思源字体子集不包含这些字符的 glyph,渲染为空白方框(□)。
|
||||
|
||||
**替代写法**:
|
||||
- 表格标记"有/无":用 `✓` `×`(思源字体支持)或中文字 `是` / `否`
|
||||
- 强调状态:用 `◆` `●` 等几何符号(字体支持)
|
||||
- 警示:用 `注:` `警告:` `※` 等文字前缀
|
||||
- 重点:用 **粗体** 或引用块,不用 emoji
|
||||
|
||||
扫描命令:
|
||||
```bash
|
||||
python3 -c "
|
||||
import re
|
||||
txt = open('final_zh_polished.md').read()
|
||||
pat = re.compile(r'[\u2700-\u27BF]|[\U0001F300-\U0001F9FF]|[\u2B00-\u2BFF]')
|
||||
hits = [(i, m.group()) for i, m in enumerate(pat.finditer(txt))]
|
||||
print(f'emoji 命中:{len(hits)} 处')
|
||||
for i, c in hits[:10]:
|
||||
print(f' 位置 {i}: {c!r} (U+{ord(c):04X})')
|
||||
"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 三、参考文献完整性校验(最关键)
|
||||
|
||||
@@ -1106,108 +1106,181 @@ def build_body(
|
||||
break
|
||||
i = first_section_idx # 从第一个 section 开始处理
|
||||
|
||||
def _title_kind(title_raw: str) -> str:
|
||||
"""识别标题的"语义类别"。无论原文 H1 或 H2,统一归类。
|
||||
|
||||
返回:
|
||||
'abstract' — 摘要(将被跳过)
|
||||
'appendix' — 附录(将被跳过)
|
||||
'version_history' — 版本历史(将被跳过)
|
||||
'toc' — 目录(自动生成)
|
||||
'references' — 参考文献(自动生成)
|
||||
'glossary' — 术语表(独立章节)
|
||||
'disclaimer' — 免责声明(独立章节)
|
||||
'executive_summary' — 执行摘要(独立章节)
|
||||
'chapter' — 正文章节(默认)
|
||||
"""
|
||||
t = title_raw.strip().lower()
|
||||
# 跳过类
|
||||
if t in ("摘要", "abstract"):
|
||||
return "abstract"
|
||||
if t.startswith("附录") or t.startswith("appendix"):
|
||||
return "appendix"
|
||||
if t in ("版本历史", "version history", "版本"):
|
||||
return "version_history"
|
||||
# 自动生成类
|
||||
if t in ("目录", "table of contents"):
|
||||
return "toc"
|
||||
if t in ("参考文献", "references", "bibliography"):
|
||||
return "references"
|
||||
# 识别类(带 PageBreak 独立成章)
|
||||
if t in ("术语表", "glossary"):
|
||||
return "glossary"
|
||||
if t in ("免责声明", "disclaimer"):
|
||||
return "disclaimer"
|
||||
if t in ("执行摘要", "executive summary", "管理层摘要"):
|
||||
return "executive_summary"
|
||||
return "chapter"
|
||||
|
||||
def _consume_until_next_section(start: int) -> int:
|
||||
"""从 start 开始收集内容(非 H1/H2 的 block),返回下一个 H1/H2 的索引。"""
|
||||
j = start
|
||||
while j < n and blocks[j].kind not in ("h1", "h2"):
|
||||
_render_generic_block(blocks[j], story, base_dir, styles, in_summary=in_summary)
|
||||
j += 1
|
||||
return j
|
||||
|
||||
def _skip_until_next_section(start: int) -> int:
|
||||
"""从 start 开始跳过内容,返回下一个 H1/H2 的索引。"""
|
||||
j = start
|
||||
while j < n and blocks[j].kind not in ("h1", "h2"):
|
||||
j += 1
|
||||
return j
|
||||
|
||||
# 收集前置件(在第一个"正文 H1 章节"之前的所有内容)按 title_kind 分组。
|
||||
# 然后按固定顺序输出:免责声明 → 执行摘要 → 目录 → 术语表 → 正文 → 参考文献。
|
||||
# 这样无论 Markdown 里写的顺序如何,最终排版都一致(目录在术语表之前)。
|
||||
first_h1_idx = n
|
||||
for k in range(i, n):
|
||||
if blocks[k].kind == "h1" and _title_kind(blocks[k].content) == "chapter":
|
||||
first_h1_idx = k
|
||||
break
|
||||
|
||||
# 收集"前置件段":从 i 到 first_h1_idx
|
||||
front_sections: dict[str, list[Block]] = {}
|
||||
|
||||
def _collect_section(start: int, until: int) -> tuple[str, list[Block], int]:
|
||||
"""从 start 处的 H1/H2 开始,收集这一 section 直到下一个 H1/H2(或 until)。
|
||||
返回 (kind, blocks 列表, 下一个 section 的起始索引)。
|
||||
"""
|
||||
head = blocks[start]
|
||||
kind = _title_kind(head.content)
|
||||
sec = [head]
|
||||
k = start + 1
|
||||
while k < until and blocks[k].kind not in ("h1", "h2"):
|
||||
sec.append(blocks[k])
|
||||
k += 1
|
||||
return kind, sec, k
|
||||
|
||||
# 在前置件区域内遍历
|
||||
k = i
|
||||
while k < first_h1_idx:
|
||||
b = blocks[k]
|
||||
if b.kind not in ("h1", "h2"):
|
||||
k += 1
|
||||
continue
|
||||
kind, sec, next_k = _collect_section(k, first_h1_idx)
|
||||
if kind in ("abstract", "appendix", "version_history"):
|
||||
pass # 丢弃
|
||||
elif kind in front_sections:
|
||||
# 重复出现:保留第一份
|
||||
pass
|
||||
else:
|
||||
front_sections[kind] = sec
|
||||
k = next_k
|
||||
|
||||
# 前置件输出顺序(固定)
|
||||
front_order = [
|
||||
"disclaimer", # 免责声明
|
||||
"executive_summary", # 执行摘要
|
||||
"toc", # 目录
|
||||
"glossary", # 术语表
|
||||
]
|
||||
|
||||
def _render_head_section(kind: str, sec: list[Block]) -> None:
|
||||
"""渲染一个前置件 section。sec[0] 是标题,其余是正文。"""
|
||||
nonlocal in_summary
|
||||
# 独立章节前加 PageBreak(但第一个除外,避免封面后空白页)
|
||||
if len(story) > 0:
|
||||
story.append(PageBreak())
|
||||
in_summary = (kind == "executive_summary")
|
||||
head = sec[0]
|
||||
|
||||
# TOC 和 references 调用专门的生成器
|
||||
if kind == "toc":
|
||||
story.extend(build_toc(blocks, styles))
|
||||
return
|
||||
if kind == "references":
|
||||
story.extend(build_references(blocks, sources_path, styles))
|
||||
return
|
||||
|
||||
# 其它前置件:H1 样式渲染标题 + 内容
|
||||
story.append(Paragraph(md_inline_to_rl(head.content), styles["h1"]))
|
||||
for sub in sec[1:]:
|
||||
# 跳过占位符段
|
||||
if sub.kind == "p" and (
|
||||
_TOC_PLACEHOLDER_RE.search(sub.content)
|
||||
or _REF_PLACEHOLDER_RE.search(sub.content)
|
||||
):
|
||||
continue
|
||||
_render_generic_block(sub, story, base_dir, styles, in_summary=in_summary)
|
||||
|
||||
for kind in front_order:
|
||||
if kind in front_sections:
|
||||
_render_head_section(kind, front_sections[kind])
|
||||
|
||||
in_summary = False
|
||||
|
||||
# 现在输出正文(从 first_h1_idx 开始)
|
||||
i = first_h1_idx
|
||||
while i < n:
|
||||
block = blocks[i]
|
||||
|
||||
# --- H1 处理(非首个;本循环内 first_section_idx 之后的 H1 都是真正的章节 H1)---
|
||||
if block.kind == "h1":
|
||||
content = block.content
|
||||
title_low = content.strip().lower()
|
||||
if block.kind not in ("h1", "h2"):
|
||||
_render_generic_block(block, story, base_dir, styles, in_summary=in_summary)
|
||||
i += 1
|
||||
continue
|
||||
|
||||
# 跳过整章:Abstract(保留 Executive Summary)
|
||||
if title_low in ("摘要", "abstract"):
|
||||
j = i + 1
|
||||
while j < n and blocks[j].kind != "h1":
|
||||
j += 1
|
||||
i = j
|
||||
continue
|
||||
kind = _title_kind(block.content)
|
||||
|
||||
# 所有非被替换的 H1 都 PageBreak
|
||||
# 跳过类
|
||||
if kind in ("abstract", "appendix", "version_history"):
|
||||
i = _skip_until_next_section(i + 1)
|
||||
continue
|
||||
|
||||
# 参考文献:自动生成
|
||||
if kind == "references":
|
||||
story.append(PageBreak())
|
||||
|
||||
if any(k in content for k in ("执行摘要", "Executive Summary", "管理层摘要")):
|
||||
in_summary = True
|
||||
else:
|
||||
in_summary = False
|
||||
|
||||
# 目录:已经 PageBreak 了,build_toc 内部再 PageBreak(独立页)
|
||||
if any(s in title_low for s in ("目录", "table of contents")):
|
||||
story.extend(build_toc(blocks, styles))
|
||||
# 跳过紧随其后的占位段
|
||||
j = i + 1
|
||||
while j < n and blocks[j].kind == "p" and _TOC_PLACEHOLDER_RE.search(blocks[j].content):
|
||||
j += 1
|
||||
i = j
|
||||
continue
|
||||
# 术语表:H1 本身已 PageBreak,末尾靠下一个 H1 自然换页
|
||||
if any(s in title_low for s in ("术语表", "glossary")):
|
||||
story.append(Paragraph(md_inline_to_rl(content), styles["h1"]))
|
||||
i += 1
|
||||
while i < n and blocks[i].kind != "h1":
|
||||
sub = blocks[i]
|
||||
_render_generic_block(sub, story, base_dir, styles, in_summary=False)
|
||||
i += 1
|
||||
continue
|
||||
if any(s in title_low for s in ("参考文献", "references")):
|
||||
story.extend(build_references(blocks, sources_path, styles))
|
||||
j = i + 1
|
||||
while j < n and blocks[j].kind == "p" and _REF_PLACEHOLDER_RE.search(blocks[j].content):
|
||||
j += 1
|
||||
i = j
|
||||
continue
|
||||
|
||||
story.append(Paragraph(md_inline_to_rl(content), styles["h1"]))
|
||||
i += 1
|
||||
story.extend(build_references(blocks, sources_path, styles))
|
||||
j = i + 1
|
||||
while j < n and blocks[j].kind == "p" and _REF_PLACEHOLDER_RE.search(blocks[j].content):
|
||||
j += 1
|
||||
i = j
|
||||
continue
|
||||
|
||||
# --- H2 同样检测占位符 ---
|
||||
if block.kind == "h2":
|
||||
title_low = block.content.strip().lower()
|
||||
|
||||
# 跳过整段:Abstract(与 Executive Summary 重复,根据用户偏好保留 Executive Summary)
|
||||
if title_low in ("摘要", "abstract"):
|
||||
# 跳到下一个 H1/H2
|
||||
j = i + 1
|
||||
while j < n and blocks[j].kind not in ("h1", "h2"):
|
||||
j += 1
|
||||
i = j
|
||||
continue
|
||||
|
||||
# 目录:前后 PageBreak(独立成页)
|
||||
if any(s in title_low for s in ("目录", "table of contents")):
|
||||
story.append(PageBreak())
|
||||
story.extend(build_toc(blocks, styles))
|
||||
j = i + 1
|
||||
while j < n and blocks[j].kind == "p" and _TOC_PLACEHOLDER_RE.search(blocks[j].content):
|
||||
j += 1
|
||||
i = j
|
||||
continue
|
||||
|
||||
# 术语表:前 PageBreak,后靠下一个 H1/H2 自然换页
|
||||
if any(s in title_low for s in ("术语表", "glossary")):
|
||||
story.append(PageBreak())
|
||||
story.append(Paragraph(md_inline_to_rl(block.content), styles["h1"]))
|
||||
i += 1
|
||||
while i < n and blocks[i].kind not in ("h1", "h2"):
|
||||
sub = blocks[i]
|
||||
_render_generic_block(sub, story, base_dir, styles, in_summary=False)
|
||||
i += 1
|
||||
continue
|
||||
|
||||
if any(s in title_low for s in ("参考文献", "references")):
|
||||
story.extend(build_references(blocks, sources_path, styles))
|
||||
j = i + 1
|
||||
while j < n and blocks[j].kind == "p" and _REF_PLACEHOLDER_RE.search(blocks[j].content):
|
||||
j += 1
|
||||
i = j
|
||||
continue
|
||||
# 目录/术语表不应在正文中出现(已经作为前置件处理)
|
||||
# 如果原文里在正文中又写了一遍目录/术语表,则跳过
|
||||
if kind in ("toc", "glossary", "disclaimer", "executive_summary"):
|
||||
i = _skip_until_next_section(i + 1)
|
||||
continue
|
||||
|
||||
# H1 正文章节(chapter):PageBreak + h1 样式
|
||||
if block.kind == "h1":
|
||||
story.append(PageBreak())
|
||||
story.append(Paragraph(md_inline_to_rl(block.content), styles["h1"]))
|
||||
else:
|
||||
# H2 正文小节:h2 样式(不分页)
|
||||
story.append(Paragraph(md_inline_to_rl(block.content), styles["h2"]))
|
||||
i += 1
|
||||
continue
|
||||
|
||||
# 非 H1/H2 的 block:统一走 _render_generic_block
|
||||
_render_generic_block(block, story, base_dir, styles, in_summary=in_summary)
|
||||
i += 1
|
||||
|
||||
return story
|
||||
|
||||
@@ -0,0 +1,146 @@
|
||||
#!/usr/bin/env python3
|
||||
"""引文完整性核查。
|
||||
|
||||
检查 final_zh_polished.md(或其它正文)中的 [src_xxx] 引用与 sources.jsonl 是否一致:
|
||||
- 孤立引用(正文有但 sources.jsonl 无):需要 dr-analyst 补信源或删这处引用
|
||||
- 孤岛信源(sources.jsonl 有但正文无):被 polish 或润色误删了上下文,或 dr-analyst 收集了
|
||||
但没用上
|
||||
- emoji 扫描:正文里不该有 emoji
|
||||
- 编号格式:检查 src_xxx 是否符合规范
|
||||
|
||||
用法:
|
||||
uv run python scripts/check_citations.py <project_slug>
|
||||
uv run python scripts/check_citations.py <project_slug> --md phase4/final_zh.md
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
EMOJI_RE = re.compile(
|
||||
r"[\U0001F000-\U0001FFFF]" # Supplementary Plane emoji
|
||||
r"|[\u2700-\u27BF]" # Dingbats (✅ ❌)
|
||||
r"|[\u2600-\u26FF]" # Misc symbols (⭐ ⚠ ☀)
|
||||
r"|[\u2B00-\u2BFF]" # Misc symbols and arrows
|
||||
)
|
||||
|
||||
# 允许的符号(字体支持)
|
||||
ALLOWED_SYMBOLS = {
|
||||
"✓", "×", "◆", "◇", "●", "○", "★", "※",
|
||||
"→", "←", "↑", "↓",
|
||||
}
|
||||
|
||||
SRC_ID_RE = re.compile(r"\[(src_[A-Za-z0-9_\-]+(?:\s*,\s*src_[A-Za-z0-9_\-]+)*)\]")
|
||||
|
||||
|
||||
def resolve_project(arg: str) -> Path:
|
||||
p = Path(arg)
|
||||
if p.is_dir():
|
||||
return p
|
||||
cand = Path.cwd() / "projects" / arg
|
||||
if cand.is_dir():
|
||||
return cand
|
||||
raise SystemExit(f"project not found: {arg}")
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description="引文完整性核查")
|
||||
parser.add_argument("project", help="项目 slug 或路径")
|
||||
parser.add_argument("--md", default="phase4/final_zh_polished.md")
|
||||
parser.add_argument("--sources", default="phase2/sources.jsonl")
|
||||
args = parser.parse_args()
|
||||
|
||||
project = resolve_project(args.project)
|
||||
md_path = project / args.md
|
||||
src_path = project / args.sources
|
||||
|
||||
if not md_path.exists():
|
||||
raise SystemExit(f"找不到正文:{md_path}")
|
||||
|
||||
text = md_path.read_text(encoding="utf-8")
|
||||
|
||||
# 1. 收集正文引用(保序去重)
|
||||
cited: list[str] = []
|
||||
cited_set: set[str] = set()
|
||||
for m in SRC_ID_RE.finditer(text):
|
||||
for sid in m.group(1).split(","):
|
||||
sid = sid.strip()
|
||||
if sid and sid not in cited_set:
|
||||
cited_set.add(sid)
|
||||
cited.append(sid)
|
||||
|
||||
# 2. 收集 sources.jsonl 中的 ID
|
||||
sources: dict[str, dict] = {}
|
||||
if src_path.exists():
|
||||
for line in src_path.read_text(encoding="utf-8").splitlines():
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
r = json.loads(line)
|
||||
if sid := r.get("id"):
|
||||
sources[sid] = r
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
orphan_cites = [s for s in cited if s not in sources]
|
||||
island_sources = [s for s in sources if s not in cited_set]
|
||||
matched = [s for s in cited if s in sources]
|
||||
|
||||
print(f"=== 引文统计 ===")
|
||||
print(f" 正文引用(独立 ID):{len(cited_set)}")
|
||||
print(f" sources.jsonl 收录:{len(sources)}")
|
||||
print(f" 匹配:{len(matched)}")
|
||||
print(f" 孤立引用(正文有 sources 无):{len(orphan_cites)}")
|
||||
print(f" 孤岛信源(sources 有正文无):{len(island_sources)}")
|
||||
|
||||
if orphan_cites:
|
||||
print(f"\n=== 孤立引用(前 20 条)===")
|
||||
for s in orphan_cites[:20]:
|
||||
print(f" {s}")
|
||||
if len(orphan_cites) > 20:
|
||||
print(f" ...还有 {len(orphan_cites) - 20}")
|
||||
print(f"\n 处理建议:")
|
||||
print(f" (a) 如果是 dr-analyst 编造的占位符 → 在正文中删除该引用")
|
||||
print(f" (b) 如果是信源未收录 → 补到 sources.jsonl")
|
||||
|
||||
if island_sources:
|
||||
print(f"\n=== 孤岛信源(前 20 条)===")
|
||||
for s in island_sources[:20]:
|
||||
print(f" {s} — {sources[s].get('title', '')[:80]}")
|
||||
if len(island_sources) > 20:
|
||||
print(f" ...还有 {len(island_sources) - 20}")
|
||||
print(f"\n 处理建议:")
|
||||
print(f" (a) 如果是 polish 阶段误删了使用该信源的段落 → 检查 polish diff")
|
||||
print(f" (b) 如果是收集多余信源 → 可以保留(build_references 会自动忽略)")
|
||||
|
||||
# 3. Emoji 扫描
|
||||
emoji_hits = []
|
||||
for m in EMOJI_RE.finditer(text):
|
||||
c = m.group()
|
||||
if c not in ALLOWED_SYMBOLS:
|
||||
line = text[:m.start()].count("\n") + 1
|
||||
emoji_hits.append((line, c))
|
||||
|
||||
if emoji_hits:
|
||||
print(f"\n=== ⚠ 发现 {len(emoji_hits)} 个 emoji(不允许出现在正文)===")
|
||||
seen = {}
|
||||
for line, c in emoji_hits:
|
||||
seen.setdefault(c, []).append(line)
|
||||
for c, lines in seen.items():
|
||||
print(f" U+{ord(c):04X} {c!r} 第 {lines[:5]} 行 等 {len(lines)} 处")
|
||||
print(f" 建议用 python3 替换:sed -i '' 's/{list(seen.keys())[0]}//g' {md_path}")
|
||||
|
||||
# 返回码:有问题返回非零便于 CI 使用
|
||||
if orphan_cites or emoji_hits:
|
||||
return 1
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -8,6 +8,7 @@
|
||||
4. **保留段落数量**:不要合并或拆分段落。每段原文对应一段输出。
|
||||
5. **专有名词首次出现保持"中文(English)"格式**;如果译文里这个术语已经这样标了就别改,也不要删掉。
|
||||
6. **不改变论点、结论、数据、案例**。只改语言表达。
|
||||
7. **严禁使用 emoji**(✅ ❌ 🔶 🔷 ⭐ 🟢 🔴 ⚠️ 💡 📌 🔑 📊 等彩色符号)。如果原文里有 emoji,替换为字体支持的符号(✓ × ◆ ● ★ * 注 等)或直接删除。这些 emoji 在 PDF 里渲染为方框。
|
||||
|
||||
## 要去掉的"AI 味/翻译腔"表征
|
||||
|
||||
|
||||
@@ -13,6 +13,7 @@ You are a senior English-to-Chinese biomedical translator and editor. You do NOT
|
||||
9. Do NOT collapse or merge consecutive paragraphs — preserve paragraph breaks.
|
||||
10. Output Chinese-style punctuation inside Chinese text: `,。;:?!""()`. Keep English punctuation inside parenthetical English phrases.
|
||||
11. Do NOT add separator lines (`---`) or blank lines that weren't in the source. If the source ends with `---`, keep it; if it doesn't, don't add one.
|
||||
12. **NEVER use emoji** (✅ ❌ 🔶 🔷 ⭐ 🟢 🔴 ⚠️ 💡 📌 🔑 📊 etc.). If the source contains emoji, replace with plain text or punctuation equivalents (✓ × ◆ ● ★ * 注 等). These do not render in the PDF (font has no glyphs).
|
||||
|
||||
## Style rules (aim for native-Chinese feel)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user