April 3, 2026
# 初始化项目信息列表
project_info_list <- list()
all_extracted_ids <- character(0)
invalid_id_records <- list()
for (issue in project_issues) {
body <- issue$body %||% ""
title <- issue$title %||% "未命名项目"
issue_number <- issue$number
# 提取学号（13位数字）
ids <- str_extract_all(body, "\\d{13}")[[1]]
ids <- unique(ids) # 去重
# 记录所有提取的学号
all_extracted_ids <- c(all_extracted_ids, ids)
# 校验学号是否合法
valid_ids <- ids[ids %in% valid_student_ids]
invalid_ids <- ids[!ids %in% valid_student_ids]
# 记录非法学号
if (length(invalid_ids) > 0) {
invalid_id_records[[length(invalid_id_records) + 1]] <- data.frame(
项目序号 = issue_number,
项目名称 = title,
非法学号 = paste(invalid_ids, collapse = ", "),
stringsAsFactors = FALSE
)
}
# 提取 GitHub 仓库链接
# 匹配 github.com/用户名/仓库名 格式
repo_urls <- str_extract_all(body, "https?://github\\.com/[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+(/[^\\s)]*)?")[[1]]
repo_url <- ifelse(length(repo_urls) > 0, repo_urls[1], NA_character_)
# 保存项目信息（只保留合法学号）
project_info_list[[length(project_info_list) + 1]] <- data.frame(
序号 = issue_number,
项目名称 = title,
成员 = paste(valid_ids, collapse = ", "),
成员数 = length(valid_ids),
仓库链接 = repo_url,
状态 = issue$state,
stringsAsFactors = FALSE
)
}
# 合并为数据框
project_info_df <- bind_rows(project_info_list) |>
arrange(序号)
# 合并非法学号记录
invalid_id_df <- bind_rows(invalid_id_records)
cat("成功提取", nrow(project_info_df), "个项目信息\n")成功提取 84 个项目信息共提取到 300 个学号其中合法学号: 293 个非法学号: 7 个| 序号 | 项目名称 | 成员 | 成员数 | 仓库链接 | 状态 |
|---|---|---|---|---|---|
| 1 | 【可重复研究项目】植物多样性对作物产量影响的复现 | 0 | — | closed | |
| 2 | 基于MediaPipe的关键点检测复现 | 2025303120173, 2025303110123, 2025303110129, 2025303120093, 2025303120174 | 5 | 链接 | open |
| 3 | RadEro v1.0.8 示例复现报告 | 2025303110072, 2025303110076, 2025303110050, 2025303120111, 2025303110075 | 5 | 链接 | open |
| 4 | 基于 YOLOv8 的实时识别 | 2025303120164, 2025303110126, 2025303110133 | 3 | 链接 | closed |
| 5 | 一种新型单一营养素水培溶液中的大豆营养-可重复研究作业 | 2025303110113, 2025303110098, 2025303120098, 2025303120112 | 4 | 链接 | open |
| 6 | 基于 OpenLandMap 数据的土壤属性预测 | 2025303110078, 2025303120145, 2025303120089 | 3 | 链接 | open |
| 7 | 基于 meanflow 的 sar2rgb 漂移模型 | 2025303120178, 2025303110131, 2025303120170, 2025303120110 | 4 | 链接 | open |
| 8 | 【可重复研究项目】土壤持水性 van Genuchten 模型复现 | 2025303120141, 2025303120150, 2025303110083 | 3 | 链接 | open |
| 9 | 滦河流域径流变化主控因子模型复现 | 2025303120031, 2025303120017, 2025303110136, 2025303120138, 2025303120126 | 5 | 链接 | open |
| 10 | 【土壤微生物311组】可重复研究项目评估 - 高寒矿区土壤微生物肥料研究 | 2025303120082, 2025303110048, 2025303120059 | 3 | 链接 | open |
| 11 | 可重复研究评估—植物表型与营养数据分析开源项目 | 2025303110106, 2025303120105, 2025303120157 | 3 | 链接 | open |
| 12 | 鸢尾花数据集的可重复数据分析 | 2025303120045, 2025303120009, 2025303120013 | 3 | 链接 | open |
| 13 | 基于Anthropogenic climate change may reduce global diazotroph diversity文献的部分数据图复现 | 2025303120033, 2025303120047, 2025303110041, 2025303120036 | 4 | 链接 | open |
| 14 | 基于点注释内场图像的大豆种子定位与计数 | 2025303120177, 2025303120002, 2025303120097, 2025303110080, 2025303110058 | 5 | 链接 | open |
| 15 | 生态阈值与火烧干扰研究 | 2025303110140, 2025303120052, 2025303120039, 2025303110036, 2025303110047 | 5 | 链接 | open |
| 16 | 土壤信息数据库及其机器学习建模 | 2025303120102, 2025303110084, 2025303110071, 2025303110018 | 4 | 链接 | open |
| 17 | 多年冻土中矿物-酶相互作用 复现 | 2025303110065, 2025303110064, 2025303120148, 2025303120023 | 4 | 链接 | open |
| 18 | [可重复研究] 凋落物分解主场效应 | 2025305110001 | 1 | — | open |
| 19 | 基于Transforming breakfast bio-waste into hydrogen storage materials文献的可重复数据分析 | 2025303110030, 2025303110034, 2025303110046, 2025303120038, 2025303120065 | 5 | 链接 | open |
| 20 | 多尺度下物种入侵悖论的复现研究 | 2025303120092, 2025303110111, 2025303120116, 2025303110109, 2025303110100 | 5 | 链接 | open |
| 21 | 关于秸秆还田土壤碳库Meta分析的研究项目复现 | 2025303120072, 2025303120094, 2025303110062, 2025303110082, 2025303110059 | 5 | 链接 | open |
| 22 | 自动流域划分算法复现 | 2025303120165, 2025303110135, 2025303120181, 2025303110138, 2025303110137 | 5 | 链接 | open |
| 23 | 可重复性评估研究-枯萎病根际微生物组的通用变异规律 | 2025303110003, 2025303120139, 2025303120076, 2025303121001, 2025303120118 | 5 | — | open |
| 24 | 基于深度残差神经网络与SAR-光学融合的Sentinel-2云去除 | 2025303110118, 2025303120172, 2025303121002 | 3 | 链接 | open |
| 25 | 基于机器学习的环境监测与定量分析的可重复性实验 | 2025303110114, 2025303110116, 2025303110122 | 3 | 链接 | open |
| 26 | 基于无人机多光谱与点云数据的植被生物物理参数估算 | 2025303120160, 2025303110001, 2025303110119, 2025303110121, 2025303120078 | 5 | 链接 | open |
| 27 | 基于像素集编码器与时间自注意力的卫星影像时间序列分类 | 2025303120175, 2025303110115, 2025303110117, 2025303110120 | 4 | 链接 | open |
| 28 | SoilGrids250m 项目可重复性评估 | 2025303120037, 2025303110103, 2025303120136 | 3 | 链接 | open |
| 29 | 中国沿海泥滩潮间带病毒的生物多样性项目复现 | 2025303110012, 2025303110006, 2025303120026 | 3 | 链接 | open |
| 30 | Crop-Recommendation-System-Using-Machine-Learning项目的可复性评估与复现 | 2025303120182, 2025303120161, 2025303120166, 2025303110125 | 4 | 链接 | open |
| 31 | 基于 DeepHighlight 项目的可重复性研究评估 | 2025317120090, 2025317120097, 2025317120099 | 3 | 链接 | open |
| 32 | 地中海橄榄园土壤侵蚀研究论文复现 | 2025303120075, 2025303120104, 2025303120131, 2025303120156, 2025303110088 | 5 | 链接 | open |
| 33 | 全球耕地氮损失复现-Nature food-Optimized agricultural management reduces global cropland nitrogen losses to air and water | 2025303110014, 2025303110095, 2025303110070, 2025303110112, 2025303110089 | 5 | 链接 | open |
| 34 | 可重复研究评估作业 - 沐禹廷 | 2025303120121, 2025303120095, 2025303120153, 2025303120099, 2025303120108 | 5 | 链接 | open |
| 35 | 农业面源污染K-Means聚类与多元回归分析 - 可重复研究项目 | 2025303110130, 2025303120061, 2025303120062 | 3 | 链接 | open |
| 36 | 关于土壤有机碳Meta分析的数据复现 | 2025303120085, 2025303120144, 2025303120060, 2025303110085, 2025303110077 | 5 | 链接 | open |
| 37 | Molecular trade-offs in soil organic carbon composition at continental scale数据复现 | 2025303110054, 2025303110056, 2025303110051 | 3 | 链接 | open |
| 38 | 全球水稻多类分割项目可复现性分析报告 | 2025303120162, 2025303120159, 2025303110124, 2025303120180 | 4 | 链接 | open |
| 39 | AgriGPTs: Research and Development of Agricultural Large Models | 2025303120163, 2025303110055, 2025303110143 | 3 | 链接 | open |
| 40 | 土壤养分与作物产量关系图复现 | 2025303120155, 2025303120129 | 2 | 链接 | open |
| 41 | 人为气候变化可能会降低全球固氮生物多样性 | 2025303120055, 2025303110013, 2025303120158, 2025303120034, 2025303110023 | 5 | 链接 | open |
| 42 | 基于 SuperCC 框架的微生物群落工程与除草剂生物修复的可重复性评估 | 2025303110052, 2025303120081 | 2 | 链接 | open |
| 43 | WRC15_Rhizo仓库根际养分与微生物群落关系图复现 | 2025303120079, 2025303110060 | 2 | 链接 | open |
| 44 | 关于济州岛柑橘园数字孪生的个性化农业潜力复现 | 2025303110027, 2025303110026, 2025303110040, 2025303110028, 2025303120146 | 5 | 链接 | open |
| 45 | CropGBWater项目可复现性评估——以 2020 年全球主粮四作物蓝绿水消耗复现为目标 | 2025303120004, 2025303110002, 2025303120167, 2025303120003 | 4 | 链接 | open |
| 46 | 基于深度学习的植物营养检测在智慧农业中的应用 | 2025303120090, 2025303120122, 2025303120152, 2025303120149, 2025303120071 | 5 | 链接 | open |
| 47 | 基于机器学习的农业肥料推荐系统 | 2025303110031, 2025303120030, 2025303110017, 2025303120010 | 4 | 链接 | open |
| 48 | 温度-深度时间序列反演饱和带土壤水分垂直通量试验的复现 | 2025303110061, 2025303120134, 2025303120124, 2025303120143, 2025303110049 | 5 | 链接 | open |
| 49 | 可重复性项目提交-Tropical cyclone rainfall extends inland | 2025303110033, 2025303120005, 2025303120142 | 3 | 链接 | open |
| 50 | 基于秀丽隐杆线虫的高通量毒性筛选：现有技术平台、核心优势与未来方向的数据复现 | 2025303110024, 2025303120025, 2025303110029, 2025303120012 | 4 | 链接 | open |
| 51 | 用于陆面模式模拟的中国土壤属性数据集的数据复现项目 | 2025303120127, 2025303120106, 2025303110090, 2025303120101, 2025303110097 | 5 | 链接 | open |
| 52 | 半干旱区植被演替过程中土壤水分对微生物碳磷代谢的调控作用复现 | 2025303120014, 2025303120044, 2025303110039, 2025303110032, 2025303110004 | 5 | 链接 | open |
| 53 | 基于功能视角的中国三峡库区经济林恢复对土壤物理质量影响评估结果复现 | 2025303110063, 2025303120073, 2025303110144 | 3 | 链接 | open |
| 54 | 土壤特性和沉积物淤积调节恢复湿地甲烷通量的可重复性评估 | 2025303110035, 2025303120063, 2025303120041 | 3 | 链接 | open |
| 55 | 氮添加对土壤微生物碳利用效率影响研究实验复现 | 2025303110022, 2025303110042, 2025303120117, 2025303120008, 2025303120107 | 5 | 链接 | open |
| 56 | 农田土壤肾形虫属原生生物内共生细菌群落特征及驱动因素可重复性评估报告 | 2025303110081, 2025303110067, 2025303120084 | 3 | — | open |
| 57 | 可重复性研究作业 | 2025303110043, 2025303120001, 2025303120029 | 3 | 链接 | open |
| 58 | 可重复性实验-【藻类胞外聚合物提取实验复现】 | 2025303110037, 2025303110044, 2025303120011, 2025303110038 | 4 | 链接 | open |
| 59 | 磷酸盐肥料农学效率研究 - 可复现性评估报告 | 2025303110104, 2025303120091, 2025303120151 | 3 | 链接 | open |
| 60 | 可重复性研究作业 | 2025303110127 | 1 | 链接 | open |
| 61 | 土壤属性制图研究的可重复性评估：基于机器学习方法的土壤属性预测及数字制图 | 2025303110128, 2025303120179, 2025303110134, 2025303120169, 2025303110125 | 5 | 链接 | open |
| 62 | 可重复性研究——中国南部地区酸性矿山废水底泥中病毒群落的分布模式及生态驱动因素 | 2025303110007, 2025303120171, 2025303120066, 2025303120140 | 4 | 链接 | open |
| 63 | 【静电耦合和水桥在生物分子于水-黏土界面吸附层级中的作用】——可重复性研究作业 | 2025303110086, 2025303110069, 2025303110079, 2025303120077, 2025303120100 | 5 | 链接 | open |
| 64 | 基与nrt的可重复性研究试验 | 2025303110141, 2025303110139, 2025303120114, 2025303120147, 2025303120110 | 5 | 链接 | open |
| 65 | Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction | 0 | — | open | |
| 66 | 基于Sustaining vulnerable agroecosystems with compost: Lasting benefits to soil health and carbon storage in semiarid winter wheat (Triticum aestivum, L.)文献的部分数据图复现 | 2025303120043, 2025303120064, 2025303110019, 2025303110073, 2025303120135 | 5 | 链接 | open |
| 67 | 可重复性研究作业 | 2025303120128 | 1 | 链接 | open |
| 68 | 大种子的智慧：种子大小本身即是一种防御策略 | 2025303110010, 2025303110008, 2025303110005, 2025303110011, 2025303110015 | 5 | 链接 | open |
| 69 | Update README.md | 0 | — | closed | |
| 70 | 全球能源消耗与碳排放情况——源自灌溉农业数据复现 | 2025303110096, 2025303110092, 2025303110107, 2025303120119 | 4 | 链接 | open |
| 71 | 细菌丰富度增强土壤有机质的热稳定性：分子多样性与热力学稳定性之间的长期权衡 论文可复现性评估 | 2025303120022, 2025303120015, 2025303120027, 2025303110025 | 4 | — | open |
| 72 | 可重复性研究 | 2025303120121, 2025303120095, 2025303120153, 2025303120099 | 4 | 链接 | open |
| 73 | 《Field Testing of Gamma-Spectroscopy Method for Soil Water Content Estimation in an Agricultural Field》可重复研究评估 | 2025303120121, 2025303120095, 2025303120153, 2025303120099 | 4 | 链接 | open |
| 74 | [个人作业] 复现评估：A reproducible R workflow to preserve variable and value labels | 2025303110132 | 1 | — | open |
| 75 | 基于《Effective treatment of Cu2+-containing acid mine drainage with acidic-cupric resistant electroactive biofilms》的可重复性研究 | 2025303110009 | 1 | 链接 | open |
| 76 | 基于开源 R 语言遥感工具包 RStoolbox 开展可重复性研究 | 2025303120176 | 1 | 链接 | open |
| 77 | 基于《Precipitation rather than temperature primarily drives global termite effects on litter decomposition》部分数据图复现 | 2025303110068 | 1 | 链接 | open |
| 78 | 基于《Transcriptional regulation of nitrogen-associated metabolism and growt》文章部分图复现 | 2025303110101, 2025303120130, 2025303110105, 2025303120083, 2025303110108 | 5 | 链接 | open |
| 79 | 基于人脸识别的项目 | 2025303120164, 2025303110126, 2025303110133 | 3 | 链接 | closed |
| 80 | 基于人脸识别的项目 | 2025303120164, 2025303110126, 2025303110133 | 3 | 链接 | open |
| 81 | Mango-Mamba 芒果叶病害轻量级检测模型结果复现 | 2025305120260 | 1 | 链接 | open |
| 82 | 个人作业 2025303110057 | 2025303110057 | 1 | — | open |
| 83 | Combined effect of molybdenum and nitrogen fertilization on nitrogen metabolism and amino acid content in tobacco leaves的复现 | 2025303120113, 2025303120069 | 2 | 链接 | open |
| 84 | 机器学习预测重金属在铁（羟基）氧化物上的吸附行为：基于吸附效率与结合构型的综合分析的可重复性研究 | 2025303110074, 2025303110053 | 2 | 链接 | open |
项目总数： 84 参与学生总数： 277 平均每个项目成员数： 3.5 # 创建成员-项目对应表
member_project_list <- list()
for (i in seq_len(nrow(project_info_df))) {
members <- unlist(strsplit(project_info_df$成员[i], ", "))
members <- members[members != ""]
# 创建带链接的项目名称
project_name <- project_info_df$项目名称[i]
issue_number <- project_info_df$序号[i]
linked_project <- paste0("[", project_name, "](https://github.com/D2RS-2026spring/projects/issues/", issue_number, ")")
for (member in members) {
member_project_list[[member]] <- c(
member_project_list[[member]],
linked_project
)
}
}
# 转换为数据框
member_df <- tibble(
学号 = names(member_project_list),
参与项目 = sapply(member_project_list, paste, collapse = "; ")
) |>
arrange(学号)
kable(member_df, caption = "学生参与项目情况")以下项目缺少仓库链接，需要跟进：| 序号 | 项目名称 | 成员 |
|---|---|---|
| 1 | 【可重复研究项目】植物多样性对作物产量影响的复现 | |
| 18 | [可重复研究] 凋落物分解主场效应 | 2025305110001 |
| 23 | 可重复性评估研究-枯萎病根际微生物组的通用变异规律 | 2025303110003, 2025303120139, 2025303120076, 2025303121001, 2025303120118 |
| 56 | 农田土壤肾形虫属原生生物内共生细菌群落特征及驱动因素可重复性评估报告 | 2025303110081, 2025303110067, 2025303120084 |
| 65 | Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction | |
| 69 | Update README.md | |
| 71 | 细菌丰富度增强土壤有机质的热稳定性：分子多样性与热力学稳定性之间的长期权衡 论文可复现性评估 | 2025303120022, 2025303120015, 2025303120027, 2025303110025 |
| 74 | [个人作业] 复现评估：A reproducible R workflow to preserve variable and value labels | 2025303110132 |
| 82 | 个人作业 2025303110057 | 2025303110057 |
# 显示非法学号详情
if (nrow(invalid_id_df) > 0) {
cat("⚠️ 发现非法学号（不在学生名单中）：\n\n")
kable(invalid_id_df, caption = "包含非法学号的项目")
# 汇总所有非法学号
all_invalid_ids <- unique(unlist(strsplit(invalid_id_df$非法学号, ", ")))
all_invalid_ids <- all_invalid_ids[all_invalid_ids != ""]
cat("\n所有非法学号列表：", paste(all_invalid_ids, collapse = ", "), "\n")
} else {
cat("✅ 所有提取的学号均在学生名单中\n")
}⚠️ 发现非法学号（不在学生名单中）：
所有非法学号列表： 0016646781000, 2643651525001, 3278740230025, 0924271620301, 1010115184451, 8329269000355, 4015755966561 # 获取已参与项目的学生（合法学号）
all_valid_members <- unlist(strsplit(project_info_df$成员, ", "))
all_valid_members <- unique(all_valid_members[all_valid_members != ""])
# 找出未参与项目的学生
unassigned <- students |>
filter(!学号 %in% all_valid_members) |>
select(学号, 姓名, 学院)
if (nrow(unassigned) > 0) {
cat("以下学生尚未加入任何项目：\n")
kable(unassigned, caption = paste0("未参与项目的学生（共", nrow(unassigned), "人）"))
} else {
cat("✅ 所有学生都已加入项目\n")
}以下学生尚未加入任何项目：| 学号 | 姓名 | 学院 |
|---|---|---|
| 2025301110128 | 杨舒桓 | 植物科学技术学院 |
| 2025303110016 | 张骏辉 | 资源与环境学院 |
| 2025303110020 | 胡金忆 | 资源与环境学院 |
| 2025303110021 | 苗芳源 | 资源与环境学院 |
| 2025303110045 | 唐成翰 | 资源与环境学院 |
| 2025303110066 | 李健萍 | 资源与环境学院 |
| 2025303110087 | 丁庆庆 | 资源与环境学院 |
| 2025303110091 | 周力 | 资源与环境学院 |
| 2025303110093 | 季佳辉 | 资源与环境学院 |
| 2025303110094 | 方立堃 | 资源与环境学院 |
| 2025303110099 | 杨冰婉 | 资源与环境学院 |
| 2025303110102 | 江祥鸿 | 资源与环境学院 |
| 2025303110110 | 陈思阳 | 资源与环境学院 |
| 2025303110142 | 李艳峰 | 资源与环境学院 |
| 2025303120018 | 师祎锴 | 资源与环境学院 |
| 2025303120024 | 张逸帆 | 资源与环境学院 |
| 2025303120042 | 王浩哲 | 资源与环境学院 |
| 2025303120067 | 于冉 | 资源与环境学院 |
| 2025303120070 | 余虹 | 资源与环境学院 |
| 2025303120074 | 刘心蕊 | 资源与环境学院 |
| 2025303120080 | 古振峰 | 资源与环境学院 |
| 2025303120086 | 孙宜宜 | 资源与环境学院 |
| 2025303120087 | 孙铭仪 | 资源与环境学院 |
| 2025303120088 | 孟雨欣 | 资源与环境学院 |
| 2025303120096 | 张恺 | 资源与环境学院 |
| 2025303120103 | 朱烁龙 | 资源与环境学院 |
| 2025303120109 | 李致远 | 资源与环境学院 |
| 2025303120115 | 梁冬玲 | 资源与环境学院 |
| 2025303120120 | 汪同宇 | 资源与环境学院 |
| 2025303120123 | 游彬 | 资源与环境学院 |
| 2025303120125 | 焦静雨 | 资源与环境学院 |
| 2025303120132 | 王硕 | 资源与环境学院 |
| 2025303120137 | 聂雅杉 | 资源与环境学院 |
| 2025303120154 | 顾湘 | 资源与环境学院 |
| 2025303120183 | 黄张赛 | 资源与环境学院 |
已参与项目学生数： 277 未参与项目学生数： 35 ---
title: "结课项目信息"
date: today
---
```{r}
#| label: setup
#| include: false
library(gh)
library(jsonlite)
library(dplyr)
library(stringr)
library(tidyr)
library(knitr)
library(purrr)
```
## 加载学生名单
```{r}
#| label: load-student-list
# 读取学生名单
students <- read.csv("data/students/student-list.csv", fileEncoding = "UTF-8-BOM")
colnames(students) <- c("学号", "姓名", "学院")
students$学号 <- as.character(students$学号)
# 创建有效学号集合
valid_student_ids <- students$学号
cat("学生名单中共有", length(valid_student_ids), "名学生\n")
```
## 从 projects 仓库获取项目信息
```{r}
#| label: fetch-projects
#| cache: true
# 获取 projects 仓库的所有 Issues
project_issues <- gh(
"GET /repos/{owner}/{repo}/issues",
owner = "D2RS-2026spring",
repo = "projects",
state = "all",
per_page = 100,
.limit = Inf
)
cat("共获取到", length(project_issues), "个项目 Issue\n")
```
## 提取项目详细信息
```{r}
#| label: extract-project-info
# 初始化项目信息列表
project_info_list <- list()
all_extracted_ids <- character(0)
invalid_id_records <- list()
for (issue in project_issues) {
body <- issue$body %||% ""
title <- issue$title %||% "未命名项目"
issue_number <- issue$number
# 提取学号（13位数字）
ids <- str_extract_all(body, "\\d{13}")[[1]]
ids <- unique(ids) # 去重
# 记录所有提取的学号
all_extracted_ids <- c(all_extracted_ids, ids)
# 校验学号是否合法
valid_ids <- ids[ids %in% valid_student_ids]
invalid_ids <- ids[!ids %in% valid_student_ids]
# 记录非法学号
if (length(invalid_ids) > 0) {
invalid_id_records[[length(invalid_id_records) + 1]] <- data.frame(
项目序号 = issue_number,
项目名称 = title,
非法学号 = paste(invalid_ids, collapse = ", "),
stringsAsFactors = FALSE
)
}
# 提取 GitHub 仓库链接
# 匹配 github.com/用户名/仓库名 格式
repo_urls <- str_extract_all(body, "https?://github\\.com/[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+(/[^\\s)]*)?")[[1]]
repo_url <- ifelse(length(repo_urls) > 0, repo_urls[1], NA_character_)
# 保存项目信息（只保留合法学号）
project_info_list[[length(project_info_list) + 1]] <- data.frame(
序号 = issue_number,
项目名称 = title,
成员 = paste(valid_ids, collapse = ", "),
成员数 = length(valid_ids),
仓库链接 = repo_url,
状态 = issue$state,
stringsAsFactors = FALSE
)
}
# 合并为数据框
project_info_df <- bind_rows(project_info_list) |>
arrange(序号)
# 合并非法学号记录
invalid_id_df <- bind_rows(invalid_id_records)
cat("成功提取", nrow(project_info_df), "个项目信息\n")
cat("共提取到", length(all_extracted_ids), "个学号\n")
cat("其中合法学号:", sum(all_extracted_ids %in% valid_student_ids), "个\n")
cat("非法学号:", sum(!all_extracted_ids %in% valid_student_ids), "个\n")
```
## 项目列表
```{r}
#| label: tbl-projects
#| tbl-cap: "作业5项目信息汇总"
# 格式化链接
display_df <- project_info_df |>
mutate(
# 项目名称链接到 ISSUE
项目名称 = paste0("[", 项目名称, "](https://github.com/D2RS-2026spring/projects/issues/", 序号, ")"),
# 仓库链接
仓库链接 = ifelse(is.na(仓库链接), "—",
paste0("[链接](", 仓库链接, ")"))
)
kable(display_df, align = c("r", "l", "l", "c", "l", "c"))
```
## 成员统计
```{r}
#| label: member-stats
# 统计总成员数
all_members <- unlist(strsplit(project_info_df$成员, ", "))
all_members <- all_members[all_members != ""]
cat("项目总数：", nrow(project_info_df), "\n")
cat("参与学生总数：", length(unique(all_members)), "\n")
cat("平均每个项目成员数：", round(mean(project_info_df$成员数), 1), "\n")
```
## 按成员查看项目
```{r}
#| label: member-projects
# 创建成员-项目对应表
member_project_list <- list()
for (i in seq_len(nrow(project_info_df))) {
members <- unlist(strsplit(project_info_df$成员[i], ", "))
members <- members[members != ""]
# 创建带链接的项目名称
project_name <- project_info_df$项目名称[i]
issue_number <- project_info_df$序号[i]
linked_project <- paste0("[", project_name, "](https://github.com/D2RS-2026spring/projects/issues/", issue_number, ")")
for (member in members) {
member_project_list[[member]] <- c(
member_project_list[[member]],
linked_project
)
}
}
# 转换为数据框
member_df <- tibble(
学号 = names(member_project_list),
参与项目 = sapply(member_project_list, paste, collapse = "; ")
) |>
arrange(学号)
kable(member_df, caption = "学生参与项目情况")
```
## 缺少仓库链接的项目
```{r}
#| label: missing-repo
missing_repo <- project_info_df |>
filter(is.na(仓库链接)) |>
select(序号, 项目名称, 成员)
if (nrow(missing_repo) > 0) {
cat("以下项目缺少仓库链接，需要跟进：\n")
kable(missing_repo, caption = "缺少仓库链接的项目")
} else {
cat("✅ 所有项目都已填写仓库链接\n")
}
```
## 学号合法性检查
```{r}
#| label: validate-student-ids
# 显示非法学号详情
if (nrow(invalid_id_df) > 0) {
cat("⚠️ 发现非法学号（不在学生名单中）：\n\n")
kable(invalid_id_df, caption = "包含非法学号的项目")
# 汇总所有非法学号
all_invalid_ids <- unique(unlist(strsplit(invalid_id_df$非法学号, ", ")))
all_invalid_ids <- all_invalid_ids[all_invalid_ids != ""]
cat("\n所有非法学号列表：", paste(all_invalid_ids, collapse = ", "), "\n")
} else {
cat("✅ 所有提取的学号均在学生名单中\n")
}
```
## 未参与项目的学生
```{r}
#| label: unassigned-students
# 获取已参与项目的学生（合法学号）
all_valid_members <- unlist(strsplit(project_info_df$成员, ", "))
all_valid_members <- unique(all_valid_members[all_valid_members != ""])
# 找出未参与项目的学生
unassigned <- students |>
filter(!学号 %in% all_valid_members) |>
select(学号, 姓名, 学院)
if (nrow(unassigned) > 0) {
cat("以下学生尚未加入任何项目：\n")
kable(unassigned, caption = paste0("未参与项目的学生（共", nrow(unassigned), "人）"))
} else {
cat("✅ 所有学生都已加入项目\n")
}
cat("\n已参与项目学生数：", length(all_valid_members), "\n")
cat("未参与项目学生数：", nrow(unassigned), "\n")
```