无效字节“？”在 2 字节序列验证/解析错误的位置 2

Question

我必须从 R igraph 中导出 graphml file 才能手动添加列值。当我想再次导入 graphml 文件时，它必须是正确的 UTF-8 和有效的 xml。因此，我使用 iconv() 在保存为 UTF-8 之前将数据转换为 UTF-8，正如您在下面我的代码的 for 循环中看到的那样

   library(igraph)
edges <- read.csv2("https://www.dropbox.com/s/p8e7hcck0d4nnrp/Subgraph_nowvalid.graphml?dl=0", header=TRUE, quote="");
amount <- nrow(edges);
amount;
sources <- data.frame(Vertexname = character(amount), Description = character(amount), Follower = numeric(amount), Friends = numeric(amount), Favourites = numeric(amount), Statuses = numeric(amount), ProfileAge = numeric(amount), Listed = numeric(amount), Timestamp = numeric(amount), OutDegree = numeric(amount), InDegree = numeric(amount), WOutDegree = numeric(amount), WInDegree = numeric(amount));
targets <- data.frame(Vertexname = character(amount), Description = character(amount), Follower = numeric(amount), Friends = numeric(amount), Favourites = numeric(amount), Statuses = numeric(amount), ProfileAge = numeric(amount), Listed = numeric(amount), Timestamp = numeric(amount), OutDegree = numeric(amount), InDegree = numeric(amount), WOutDegree = numeric(amount), WInDegree = numeric(amount));

for (i in 1:ncol(edges)) {
    edges[,i] <- iconv(edges[,i], to="UTF-8", sub="");
    if (is.character(edges[,i])) {
        edges[,i] <- gsub("[[:cntrl:]]", "", edges[,i])
    }
}

sources[,1] <- edges[,1];
sources[,2:8] <- NA;
sources[,9] <- edges[,4];
sources[,10:13] <- NA;
targets[,1] <- edges[,2];
targets[,2] <- edges[,7];
targets[,3] <- edges[,8];
targets[,4] <- edges[,9];
targets[,5] <- edges[,10];
targets[,6] <- edges[,11];
targets[,7] <- edges[,12];
targets[,8] <- edges[,13];
targets[,9:13] <- NA;

print("REPORT: vertices data frames filled")

sources <- unique(sources);
targets <- unique(targets);
print("REPORT: Duplicated sources and targets removed");

nodes <- within(merge(sources, targets, by="Vertexname", all=TRUE), {
            Description <- ifelse(is.na(Description.x), paste(Description.y), Description.x); Description.x = NULL; Description.y = NULL; 
            Follower <- ifelse(is.na(Follower.x), Follower.y, Follower.x); Follower.x = NULL; Follower.y = NULL; 
            Friends <- ifelse(is.na(Friends.x), Friends.y, Friends.x); Friends.x = NULL; Friends.y = NULL;
            Favourites <- ifelse(is.na(Favourites.x), Favourites.y, Favourites.x); Favourites.x = NULL; Favourites.y = NULL;
            Statuses <- ifelse(is.na(Statuses.x), Statuses.y, Statuses.x); Statuses.x = NULL; Statuses.y = NULL;
            ProfileAge <- ifelse(is.na(ProfileAge.x), ProfileAge.y, ProfileAge.x); ProfileAge.x = NULL; ProfileAge.y = NULL;
            Listed <- ifelse(is.na(Listed.x), Listed.y, Listed.x); Listed.x = NULL; Listed.y = NULL;
            Timestamp <- ifelse(is.na(Timestamp.y), Timestamp.x, Timestamp.y); Timestamp.x = NULL; Timestamp.y = NULL;
            OutDegree <- ifelse(is.na(OutDegree.x), OutDegree.y, OutDegree.x); OutDegree.x = NULL; OutDegree.y = NULL;
            InDegree <- ifelse(is.na(InDegree.x), InDegree.y, InDegree.x); InDegree.x = NULL; InDegree.y = NULL;
            WOutDegree <- ifelse(is.na(WOutDegree.x), WOutDegree.y, WOutDegree.x); WOutDegree.x = NULL; WOutDegree.y = NULL;
            WInDegree <- ifelse(is.na(WInDegree.x), WInDegree.y, WInDegree.x); WInDegree.x = NULL; WInDegree.y = NULL});
print("REPORT: Sources and Targets merged");

nodes <- subset(nodes, !duplicated(nodes$Vertexname));
print("REPORT: Duplicated vertices removed");

nrow(nodes);

edges <- edges[complete.cases(edges[,1:2]),];
nodes <- nodes[complete.cases(nodes[,1]),];
print("REPORT: Invalid edges and nodes removed");

g <- graph.data.frame(edges, directed=TRUE, nodes);
print("REPORT: Graph created");

outdegrees <- degree(g, v=V(g), mode="out");
indegrees <- degree(g, v=V(g), mode="in");
woutdegrees <- graph.strength(g, v=V(g), mode="out");
windegrees <- graph.strength(g, v=V(g), mode="in");
g <- set.vertex.attribute(g, "OutDegree", V(g), outdegrees);
g <- set.vertex.attribute(g, "InDegree", V(g), indegrees);
g <- set.vertex.attribute(g, "WOutDegree", V(g), woutdegrees);
g <- set.vertex.attribute(g, "WInDegree", V(g), windegrees);
print("REPORT: Degree calculated and added as vertex attribute");

# Filter

nodes <- get.data.frame(g, "vertices");
nodes <- nodes[order(nodes$OutDegree, decreasing = TRUE),];
nrow(nodes);
minOutDegree <- nodes[1335,"OutDegree"]; # 1335
minOutDegree;
nodes <- nodes[order(nodes$InDegree, decreasing = TRUE),];
minInDegree <- nodes[1335,"InDegree"];
minInDegree;

nodes2 <- subset(nodes, nodes$OutDegree >= minOutDegree | nodes$InDegree >= minInDegree);
nrow(nodes2);
nodes3 <- subset(nodes, nodes$OutDegree >= minOutDegree & nodes$InDegree >= minInDegree);
nrow(nodes3);

g <- set.vertex.attribute(g, "Group", V(g), NA);
g <- induced.subgraph(g, V(g)$OutDegree >= minOutDegree | V(g)$InDegree >= minInDegree);
length(E(g));
length(V(g));
g <- induced.subgraph(g, V(g)$OutDegree > 0 & V(g)$InDegree > 0);
length(E(g));
length(V(g));
g <- induced.subgraph(g, V(g)$OutDegree > (V(g)$InDegree / 3));
length(E(g));
length(V(g));
write.graph(g, "SomePath");
print("REPORT: Subgraph Test saved");

当我再次使用 read.graph 导入 graphml 文件时，我得到了错误：

Error in .Call("R_igraph_read_graph_graphml", file, as.numeric(index),  : 
  At foreign-graphml.c:1202 :  
å
, Parse error

因此我使用 XMLValidatorBuddy 来验证 graphml 文件（在下拉字段中选择了 UTF-8 作为使用的编码，但无论选择哪种编码都会发生错误）。这是我得到错误的地方：

无效字节'?'在 2 字节序列的第 2 位

根据 XMLValidatorBuddy，错误发生在第 4278 行。

this 问题的答案对我没有帮助，因为由于 R 中的转换，我应该有一个 UTF-8 编码的 graphml 文件。

Answer 1

这行肯定是错误的：

edges[,i] <- gsub("[[:ctrl:]]", "", edges[,i])

我看到它的目的是从边缘属性中去除任何不允许的控制字符，这样您就不会在使用 GraphML 编写器时遇到任何麻烦，但[[:ctrl:]] 应该是[[:cntrl:]]。 （实际上，我的 R 版本在看到 [[:ctrl:]] 时会报错，但也许你的不会）。

另外，在将字符串转换为 UTF-8 后，我会避免弄乱字符串的单个字符。如果要从字符串中去除控制字符，请在转换为 UTF-8 之前执行此操作。由于 UTF-8 编码的工作原理，字符代码小于 128 的 Unicode 字符（包含您担心的所有控制字符）保持不变，并且 UTF-8 编码不会引入任何额外的 ASCII 字符字符码小于 128。