1. 修复博客地址配置错误

2. 修复进度条打印失败的问题。删掉不必要的日志

Author: Estom

.vscode/launch.json

@@ -16,7 +16,20 @@
             "env": {
                 "HF_ENDPOINT": "https://hf-mirror.com"
             },
-            "args": "--verbose --git-batch=true --tag-count=3 --tag-method=keybert"
+            "args": "--verbose --git-batch=true --tag-count=0 --tag-method=keybert"
+        },
+        {
+            "name": "Python数据同步 (.venv)",
+            "type": "debugpy",
+            "request": "launch",
+            "cwd": "${workspaceFolder}",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "python": "${workspaceFolder}/.venv/bin/python",
+            "env": {
+                "HF_ENDPOINT": "https://hf-mirror.com"
+            },
+            "args": "--verbose"
         },
         {
             "name": "Python数据处理 (uv run + attach)",

TODO.md

@@ -52,7 +52,7 @@
 - [ ] 工程化指南
   - [TODO] ~~将数据处理的脚本，整理为python的模块。~~
   - [x] 通过.env定义环境变量和参数。给出.env.example文件，给出参数说明。.env本身不要提交到git中。
-  - [TODO] README.md 包括项目说明、快速开始。
+  - [x] README.md 包括项目说明、快速开始。
 
 CICI 流水线的过程。Github Actions流水线-> Dockerfile镜像构建 -> build.sh 构建脚本 -> uv/npm构建工具 -> python和nodejs工程。
 1. notes工程开发

_config.yml

@@ -13,7 +13,7 @@ timezone: 'Asia/Shanghai'
 
 # URL
 ## Set your site url here. For example, if you use GitHub Page, set url as 'https://username.github.io/project'
-url: https://estom.github.com
+url: https://estom.github.io
 # root: /hexo-blog/
 permalink: :year/:month/:day/:title/
 permalink_defaults:

docker.sh

@@ -1,13 +1,13 @@
 # 基础镜像没有变化，不需要每次重新构建
 # docker build -t ghcr.io/estom/hexo-blog:base-v1.0.0 -f Dockerfile-base .
 # docker push ghcr.io/estom/hexo-blog:base-v1.0.0
-docker build -t ghcr.io/estom/hexo-blog:build-v1.0.0 -f Dockerfile-build .
-docker push ghcr.io/estom/hexo-blog:build-v1.0.0
-docker build -t ghcr.io/estom/hexo-blog:run-v1.0.0 -f Dockerfile-runtime .
-docker push ghcr.io/estom/hexo-blog:run-v1.0.0
+# docker build -t hexo-blog:build-v1.0.0 -f Dockerfile-build .
+# docker push hexo-blog:build-v1.0.0
+docker build -t hexo-blog:run-v1.0.0 -f Dockerfile .
+# docker push hexo-blog:run-v1.0.0
 
 # 运行基础镜像
-docker run -d --name notes -p 80:80 ghcr.io/estom/hexo-blog:run-v1.0.0
+docker run -d --name notes -p 80:80 hexo-blog:run-v1.0.0
 
 # 本地启动hexo 服务器。不适用docker打包的方式
 # nohup hexo server -p 4001 > hexo.log 2&>1  &
@@ -18,4 +18,4 @@ docker run -d --name notes -p 80:80 ghcr.io/estom/hexo-blog:run-v1.0.0
 
 # 更新子模块，会触发子模块的下载
 # git submodule update --recursive
-uv run hexo-proc --verbose --git-batch=true --tag-method=keybert --tag-count=3 --tag-budget=100
+# uv run hexo-proc --verbose --git-batch=true --tag-method=keybert --tag-count=3 --tag-budget=100

processor/proc.py

@@ -58,9 +58,9 @@ class ProgressPrinter:
 
 	def __post_init__(self) -> None:
 		if not self.enabled:
-			self._is_tty = False
 			return
 		self._is_tty = bool(getattr(self.tty_stream, "isatty", lambda: False)())
+		print(f"[tags] enabled: {self.enabled},is_tty: {self._is_tty}")
 
 	def _render_bar(self, done: int, total: int) -> str:
 		if total <= 0:
@@ -861,8 +861,8 @@ def _build_git_time_index(repo_dir: Path, interest_paths: Set[str], date_kind: s
 	created: Dict[str, int] = {}
 	done: Set[str] = set()
 	current_ts: Optional[int] = None
-	progress = ProgressPrinter(enabled=verbose, prefix='[git] batch')
-	last_filled = -1
+	progress = ProgressPrinter(enabled=verbose, prefix='[git] scan')
+	total_lines = 0
 
 	try:
 		with tempfile.NamedTemporaryFile(prefix='git-log-', suffix='.txt', delete=False, mode='w', encoding='utf-8') as fp:
@@ -888,8 +888,14 @@ def _build_git_time_index(repo_dir: Path, interest_paths: Set[str], date_kind: s
 
 		if out_path is None:
 			return {}
+
+		# Progress: use processed line count / total line count.
+		# Only compute total_lines when verbose to avoid an extra full pass.
+		with open(out_path, 'r', encoding='utf-8', errors='replace') as f_total:
+			total_lines = sum(1 for _ in f_total)
+
 		with open(out_path, 'r', encoding='utf-8', errors='replace') as f:
-			for line in f:
+			for line_no, line in enumerate(f, start=1):
 				s = line.rstrip('\n')
 				if not s:
 					continue
@@ -903,6 +909,8 @@ def _build_git_time_index(repo_dir: Path, interest_paths: Set[str], date_kind: s
 					continue
 
 				parts = s.split('\t')
+				if len(parts) < 2:
+					continue
 				status = parts[0]
 				# Rename: Rxxx\told\tnew
 				if status.startswith('R') and len(parts) >= 3:
@@ -921,8 +929,7 @@ def _build_git_time_index(repo_dir: Path, interest_paths: Set[str], date_kind: s
 					created[final] = current_ts
 					continue
 
-				if len(parts) < 2:
-					continue
+
 				path = parts[1]
 				if path in interest_paths:
 					final = path
@@ -933,18 +940,8 @@ def _build_git_time_index(repo_dir: Path, interest_paths: Set[str], date_kind: s
 
 				updated.setdefault(final, current_ts)
 				created[final] = current_ts
-				if status == 'A':
-					done.add(final)
-					if len(done) == len(interest_paths):
-						break
-
-				filled = 0
-				for k in interest_paths:
-					if k in updated and k in created:
-						filled += 1
-				if filled != last_filled:
-					progress.update(filled, len(interest_paths))
-					last_filled = filled
+				# Throttle progress updates to reduce TTY overhead.
+				progress.update(line_no, total_lines)
 	finally:
 		if out_path:
 			try:
@@ -958,7 +955,8 @@ def _build_git_time_index(repo_dir: Path, interest_paths: Set[str], date_kind: s
 		u = updated.get(k)
 		if c is not None and u is not None:
 			result[k] = (c, u)
-	progress.close(len(interest_paths))
+	# Mark progress completed (even if we early-stopped).
+	progress.close(total_lines)
 	return result
 
 
@@ -1128,8 +1126,8 @@ def process_directory(cfg: ProcessConfig) -> int:
 	for i, p in enumerate(files, start=1):
 		if process_file(cfg, p):
 			count += 1
-			if cfg.verbose:
-				print(f"[ok] {p.relative_to(cfg.target_dir).as_posix()}")
+			# if cfg.verbose:
+			# 	print(f"[ok] {p.relative_to(cfg.target_dir).as_posix()}")
 		progress.update(i, total)
 	progress.close(total)