添加仓库完整性体检原始数据与扫描脚本

analysis/README.md

@@ -0,0 +1,26 @@
+# 仓库完整性体检原始数据
+
+本目录存放《低功耗 RISC-V 开源芯片综述》第 7 节（仓库完整性与可二次开发性实测评估）的原始数据与可复现工具。
+
+| 文件 | 说明 |
+|---|---|
+| `scan_repos.py` | 结构化体检脚本（统计 RTL 规模、验证环境、构建体系、CI、依赖管理等） |
+| `仓库体检原始输出.txt` | 2026-09-06 对 9 个仓库的实际扫描输出 |
+
+## 复现方法
+
+体检时各仓库以浅克隆方式获取（`git clone --depth 1`），扫描脚本直接对本地目录统计：
+
+```bash
+git clone --depth 1 https://github.com/olofk/serv.git            # 其余 8 仓同理
+python3 scan_repos.py > 仓库体检原始输出.txt
+```
+
+## 扫描口径
+
+- **RTL 行数**：`.v/.sv/.svh/.vh/.vhd/.vhdl/.scala` 源码文件行数合计（VexRiscv 含 SpinalHDL 源码）
+- **验证环境**：tb/testbench/verif/dv/uvm/tests 等典型验证目录下的 RTL 文件计数
+- **构建体系**：FuseSoC `.core`、Makefile、Bazel（build/.bzl）、CMake、Tcl 脚本计数
+- **依赖管理**：`.gitmodules` 子模块清单；清单式外拉（pulpino `update-ips.py`、pulpissimo Bender）需结合 README 人工核查
+
+注意：`git log` 显示的 HEAD 日期为扫描时点（2026-09-06）状态，各仓库后续会有新提交。

analysis/scan_repos.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""Scan cloned RISC-V repos and print a compact completeness report."""
+import os, subprocess, io, sys
+
+sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8")
+REPO_DIR = "/data/repos"
+REPOS = ["serv", "neorv32", "picorv32", "ibex", "VexRiscv",
+         "e203_hbirdv2", "pulpino", "pulpissimo", "opentitan"]
+
+RTL_EXT = {".v", ".sv", ".svh", ".vh", ".vhd", ".vhdl", ".fhdl", ".scala"}
+TB_DIRS = {"tb", "tb_core", "testbench", "verif", "dv", "dv_uvm", "tests", "test", "tbench"}
+DOC_EXT = {".md", ".rst", ".tex", ".pdf"}
+
+def head_date(repo):
+    try:
+        out = subprocess.run(["git", "log", "-1", "--format=%ci %h"],
+                             cwd=os.path.join(REPO_DIR, repo), capture_output=True, text=True).stdout
+        return out.strip()[:16]
+    except Exception:
+        return "?"
+
+def scan(repo):
+    root = os.path.join(REPO_DIR, repo)
+    rtl_files = rtl_lines = doc_files = tb_rtl = 0
+    core_files = makefiles = pyscripts = tcl = bazel = cmake = 0
+    workflows, licenses = [], []
+    gitmods = []
+    for dirpath, dirnames, filenames in os.walk(root):
+        dirnames[:] = [d for d in dirnames if d != ".git"]
+        rel = os.path.relpath(dirpath, root)
+        parts = set(rel.replace("\\", "/").split("/"))
+        for f in filenames:
+            p = os.path.join(dirpath, f)
+            ext = os.path.splitext(f)[1].lower()
+            lf = f.lower()
+            if ext in RTL_EXT:
+                try:
+                    with open(p, "rb") as fh:
+                        n = sum(1 for _ in fh)
+                except Exception:
+                    n = 0
+                rtl_files += 1
+                rtl_lines += n
+                if parts & TB_DIRS:
+                    tb_rtl += 1
+            elif ext in DOC_EXT:
+                doc_files += 1
+            if lf == "license" or lf.startswith("license."):
+                licenses.append(os.path.relpath(p, root))
+            if lf.endswith(".core"):
+                core_files += 1
+            if lf in ("makefile",) or lf.startswith("makefile.") or lf.endswith(".mk"):
+                makefiles += 1
+            if ext == ".py":
+                pyscripts += 1
+            if ext == ".tcl":
+                tcl += 1
+            if lf.startswith("bazelrc") or lf == "build" or lf.endswith(".bzl") or lf == "module_bazel":
+                bazel += 1
+            if lf in ("cmakelists.txt",):
+                cmake += 1
+        if rel == os.path.join(".github", "workflows"):
+            workflows = [f for f in filenames if f.endswith((".yml", ".yaml"))]
+    gm = os.path.join(root, ".gitmodules")
+    if os.path.exists(gm):
+        with open(gm, encoding="utf-8", errors="ignore") as fh:
+            gitmods = [l.split("=", 1)[1].strip() for l in fh if l.strip().startswith("path =")]
+    tops = sorted(d for d in os.listdir(root)
+                  if os.path.isdir(os.path.join(root, d)) and d != ".git")
+    lic = licenses[0] if licenses else "MISSING"
+    readme = os.path.exists(os.path.join(root, "README.md")) or os.path.exists(os.path.join(root, "README.rst"))
+    print(f"=== {repo} ===")
+    print(f"HEAD: {head_date(repo)} | LICENSE: {lic} | README: {'Y' if readme else 'N'}")
+    print(f"RTL files: {rtl_files} | RTL lines: {rtl_lines} | TB rtl files: {tb_rtl} | doc files: {doc_files}")
+    print(f"FuseSoC .core: {core_files} | Makefile: {makefiles} | .py: {pyscripts} | .tcl: {tcl} | bazel-ish: {bazel} | cmake: {cmake}")
+    print(f"CI workflows: {len(workflows)} {workflows[:4]}")
+    print(f"submodules({len(gitmods)}): {gitmods[:12]}")
+    print(f"top dirs: {tops}")
+    print()
+
+for r in REPOS:
+    try:
+        scan(r)
+    except Exception as e:
+        print(f"=== {r} === ERROR {e}\n")

analysis/仓库体检原始输出.txt

@@ -0,0 +1,72 @@
+=== serv ===
+HEAD: 2026-08-25 14:38 | LICENSE: LICENSE | README: Y
+RTL files: 78 | RTL lines: 6701 | TB rtl files: 0 | doc files: 14
+FuseSoC .core: 4 | Makefile: 2 | .py: 4 | .tcl: 10 | bazel-ish: 0 | cmake: 5
+CI workflows: 5 ['openlane.yml', 'lint.yml', 'ci.yml', 'pages.yml']
+submodules(0): []
+top dirs: ['.github', 'bench', 'data', 'doc', 'rtl', 'servant', 'servile', 'serving', 'sw', 'verif', 'zephyr']
+
+=== neorv32 ===
+HEAD: 2026-09-06 08:37 | LICENSE: LICENSE | README: Y
+RTL files: 74 | RTL lines: 28094 | TB rtl files: 0 | doc files: 25
+FuseSoC .core: 0 | Makefile: 38 | .py: 0 | .tcl: 1 | bazel-ish: 0 | cmake: 0
+CI workflows: 3 ['Processor.yml', 'Verilog.yml', 'Documentation.yml']
+submodules(0): []
+top dirs: ['.github', 'docs', 'rtl', 'sim', 'sw']
+
+=== picorv32 ===
+HEAD: 2026-07-31 17:45 | LICENSE: tests/LICENSE | README: Y
+RTL files: 41 | RTL lines: 9133 | TB rtl files: 0 | doc files: 4
+FuseSoC .core: 5 | Makefile: 11 | .py: 8 | .tcl: 8 | bazel-ish: 0 | cmake: 0
+CI workflows: 1 ['ci.yml']
+submodules(0): []
+top dirs: ['.github', 'dhrystone', 'firmware', 'picosoc', 'scripts', 'tests']
+
+=== ibex ===
+HEAD: 2026-08-31 07:52 | LICENSE: LICENSE | README: Y
+RTL files: 654 | RTL lines: 109042 | TB rtl files: 266 | doc files: 120
+FuseSoC .core: 209 | Makefile: 50 | .py: 200 | .tcl: 24 | bazel-ish: 7 | cmake: 0
+CI workflows: 5 ['private-ci.yml', 'cla.yml', 'ci.yml', 'ci-formal.yml']
+submodules(0): []
+top dirs: ['.github', 'ci', 'doc', 'dv', 'examples', 'formal', 'lint', 'nix', 'rtl', 'shared', 'syn', 'util', 'vendor']
+
+=== VexRiscv ===
+HEAD: 2026-08-31 17:50 | LICENSE: LICENSE | README: Y
+RTL files: 122 | RTL lines: 27279 | TB rtl files: 13 | doc files: 8
+FuseSoC .core: 0 | Makefile: 34 | .py: 5 | .tcl: 9 | bazel-ish: 0 | cmake: 0
+CI workflows: 1 ['scala.yml']
+submodules(1): ['src/test/resources/VexRiscvRegressionData']
+top dirs: ['.github', 'assets', 'doc', 'project', 'scripts', 'src']
+
+=== e203_hbirdv2 ===
+HEAD: 2025-08-06 10:51 | LICENSE: LICENSE | README: Y
+RTL files: 141 | RTL lines: 57651 | TB rtl files: 1 | doc files: 20
+FuseSoC .core: 2 | Makefile: 13 | .py: 12 | .tcl: 16 | bazel-ish: 0 | cmake: 0
+CI workflows: 1 ['deploy_doc.yaml']
+submodules(0): []
+top dirs: ['.github', 'doc', 'fpga', 'pics', 'riscv-tools', 'rtl', 'tb', 'vsim']
+
+=== pulpino ===
+HEAD: 2019-05-29 11:29 | LICENSE: LICENSE | README: Y
+RTL files: 49 | RTL lines: 10608 | TB rtl files: 12 | doc files: 23
+FuseSoC .core: 0 | Makefile: 51 | .py: 22 | .tcl: 25 | bazel-ish: 0 | cmake: 118
+CI workflows: 0 []
+submodules(0): []
+top dirs: ['ci', 'doc', 'fpga', 'ips', 'rtl', 'sw', 'tb', 'vsim']
+
+=== pulpissimo ===
+HEAD: 2024-05-30 19:02 | LICENSE: LICENSE.md | README: Y
+RTL files: 107 | RTL lines: 87497 | TB rtl files: 11 | doc files: 52
+FuseSoC .core: 1 | Makefile: 46 | .py: 42 | .tcl: 70 | bazel-ish: 0 | cmake: 0
+CI workflows: 1 ['gitlab-ci.yml']
+submodules(2): ['sw/pulp-runtime', 'sw/regression_tests']
+top dirs: ['.github', 'doc', 'hw', 'sw', 'target', 'utils']
+
+=== opentitan ===
+HEAD: 2026-09-04 20:21 | LICENSE: LICENSE | README: Y
+RTL files: 3995 | RTL lines: 1156179 | TB rtl files: 2670 | doc files: 885
+FuseSoC .core: 821 | Makefile: 31 | .py: 667 | .tcl: 137 | bazel-ish: 794 | cmake: 0
+CI workflows: 12 ['cherrypick.yml', 'private-ci.yml', 'pr_change_check.yml', 'monthly.yml']
+submodules(0): []
+top dirs: ['.github', 'ci', 'doc', 'hw', 'quality', 'release', 'rules', 'signing', 'site', 'sw', 'third_party', 'toolchain', 'util']
+