fixing-claude-export-conversations

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Fixing Claude Code Export Conversations

修复Claude Code导出的对话文件

Reconstruct broken line wrapping in Claude Code exported

.txt

files.

重构Claude Code导出的

.txt

文件中损坏的换行格式。

Quick Start

快速开始

bash

undefined

bash

undefined

Fix and show stats

修复并显示统计信息

uv run <skill-path>/scripts/fix-claude-export.py <export.txt> --stats

Custom output

自定义输出

uv run <skill-path>/scripts/fix-claude-export.py <export.txt> -o fixed.txt

Validate the result (53 automated checks)

验证结果（包含53项自动检查）

uv run <skill-path>/scripts/validate-claude-export-fix.py <export.txt> fixed.txt


Replace `<skill-path>` with the resolved path to this skill's directory. Find it with:
```bash
find ~/.claude -path "*/fixing-claude-export-conversations/scripts" -type d 2>/dev/null

uv run <skill-path>/scripts/validate-claude-export-fix.py <export.txt> fixed.txt


将`<skill-path>`替换为该skill目录的实际路径。可通过以下命令查找：
```bash
find ~/.claude -path "*/fixing-claude-export-conversations/scripts" -type d 2>/dev/null

Workflow

工作流程

Copy this checklist and track progress:

- [ ] Step 1: Locate the exported .txt file
- [ ] Step 2: Run fix script with --stats
- [ ] Step 3: Run validation suite
- [ ] Step 4: Spot-check output (tables, CJK paragraphs, tool results)
- [ ] Step 5: Deliver fixed file to user

Step 1: Locate the file. Claude Code exports use the naming pattern

YYYY-MM-DD-HHMMSS-<slug>.txt

Step 2: Run the fix script.

bash

uv run <skill-path>/scripts/fix-claude-export.py <input.txt> -o <output.txt> --stats

Review the stats output — typical results: 20-25% line reduction, 80+ table borders fixed, 160+ table cells fixed.

Step 3: Run the validation suite.

bash

uv run <skill-path>/scripts/validate-claude-export-fix.py <input.txt> <output.txt>

All checks must pass. If any fail, investigate before delivering. Use

--verbose

for full details on passing checks too.

Step 4: Spot-check. Open the output and verify:

Tables have intact borders (box-drawing characters on single lines)
CJK/English mixed text has pangu spacing (
```
Portal 都需要
```
, not
```
Portal都需要
```
)
Tool result blocks (
```
⎿
```
) have complete content on joined lines
Diff output within tool results has each line number on its own line

Step 5: Deliver the fixed file to the user.

复制以下检查清单并跟踪进度：

- [ ] 步骤1：找到导出的.txt文件
- [ ] 步骤2：运行修复脚本并添加--stats参数
- [ ] 步骤3：运行验证套件
- [ ] 步骤4：抽查输出内容（表格、中日韩段落、工具结果）
- [ ] 步骤5：将修复后的文件交付给用户

步骤1：找到文件。Claude Code导出文件的命名格式为

YYYY-MM-DD-HHMMSS-<slug>.txt

。

步骤2：运行修复脚本

bash

uv run <skill-path>/scripts/fix-claude-export.py <input.txt> -o <output.txt> --stats

查看统计输出——典型结果：行数减少20-25%，修复80+个表格边框，修复160+个表格单元格。

步骤3：运行验证套件

bash

uv run <skill-path>/scripts/validate-claude-export-fix.py <input.txt> <output.txt>

所有检查必须通过。如果有任何检查失败，在交付前需进行调查。使用

--verbose

参数可查看所有通过检查的详细信息。

步骤4：抽查。打开输出文件并验证：

表格边框完整（框线字符在单行显示）
中日韩/英文混合文本有Pangu空格（如
```
Portal 都需要
```
，而非
```
Portal都需要
```
）
工具结果块（
```
⎿
```
前缀）的内容已完整合并到单行
工具结果中的Diff输出每行的行号单独显示

步骤5：交付修复后的文件给用户。

What Gets Fixed

修复内容

The script handles 10 content types using a state-machine with next-line look-ahead:

User prompts (
```
❯
```
prefix, dw=76 padding) — paragraph joins with pangu spacing
Claude responses (
```
●
```
prefix) — narrative, bullet, and numbered list joins
Claude paragraphs (2-space indent) — next-line look-ahead via
```
_is_continuation_fragment
```
Tables — border reconstruction, cell re-padding with pipe-count tracking
Tool calls (
```
● Bash(
```
etc.) — path and argument reconstruction
Tool results (
```
⎿
```
prefix) — continuation joins including deeper-indented fragments
Plan text (5-space indent) — next-line look-ahead via
```
_is_plan_continuation_fragment
```
Agent tree (
```
├─
```
/
```
└─
```
) — preserved structure
Separators (
```
────
```
,
```
---
```
) — never joined
Tree connectors (standalone
```
│
```
) — preserved

该脚本使用带下一行前瞻的状态机处理10种内容类型：

用户提示（
```
❯
```
前缀，dw=76填充）——段落合并并添加Pangu空格
Claude回复（
```
●
```
前缀）——叙述内容、项目符号和编号列表合并
Claude段落（2空格缩进）——通过
```
_is_continuation_fragment
```
进行下一行前瞻
表格——边框重构，通过管道计数跟踪重新填充单元格
工具调用（
```
● Bash(
```
等）——路径和参数重构
工具结果（
```
⎿
```
前缀）——合并连续内容，包括更深缩进的片段
计划文本（5空格缩进）——通过
```
_is_plan_continuation_fragment
```
进行下一行前瞻
Agent树（
```
├─
```
/
```
└─
```
）——保留结构
分隔符（
```
────
```
,
```
---
```
）——从不合并
树连接器（独立的
```
│
```
）——保留结构

Key Design Decisions

关键设计决策

Next-line look-ahead (not dw thresholds): Instead of asking "was this line wrapped?" (fragile threshold), the script asks "does the next line look like a continuation?" by examining its content patterns — lowercase start, CJK ideograph start, opening bracket, hyphen/slash/underscore continuation.

Pangu spacing: Inserts spaces between ASCII alphanumeric characters and CJK ideographs at join boundaries. Also triggers for

adjacent to CJK.

Mid-token detection: Joins without space when boundaries indicate identifiers (

BASE_

URL

), paths (

documents

/05-team

), or hyphenated names (

ready

-together

). Exception:

--

prefix gets a space (

run

--headed

下一行前瞻（而非dw阈值）：不是判断“这行是否被换行？”（脆弱的阈值），而是通过检查内容模式判断“下一行看起来是否是延续内容？”——比如以小写字母开头、中日韩汉字开头、左括号开头、连字符/斜杠/下划线延续等。

Pangu空格：在ASCII字母数字字符和中日韩汉字的合并边界插入空格。当

、

与中日韩汉字相邻时也会触发。

中间标记检测：当边界表示标识符（如

BASE_

URL

）、路径（如

documents

/05-team

）或连字符名称（如

ready

-together

）时，无空格合并。例外：

--

前缀前添加空格（如

run

--headed

）。

Safety

安全性

Never modifies the original file
Marker counts verified:
```
❯
```
,
```
●
```
,
```
✻
```
,
```
⎿
```
,
```
…
```
must match input/output
Runaway join detection: warns if any line exceeds 500 display-width
Strict UTF-8 encoding — no silent fallbacks

从不修改原始文件
验证标记计数：
```
❯
```
、
```
●
```
、
```
✻
```
、
```
⎿
```
、
```
…
```
在输入和输出中必须一致
失控合并检测：如果任何行超过500显示宽度则发出警告
严格UTF-8编码——无静默回退

Dependencies

依赖项

Python 3.10+ via

uv run

— zero external packages (stdlib only:

unicodedata

argparse

re

pathlib

dataclasses

通过

uv run

运行Python 3.10+——零外部包（仅使用标准库：

unicodedata

、

argparse

、

re

、

pathlib

、

dataclasses

）。