Decode local paths from drop payloads

Drops arrive as a CRLF-separated text/uri-list of file URLs, so every
consumer percent-decodes them; wsap_term does it in its own drop code.

yasl_drop_next_path() walks the list and returns one decoded local path
at a time. It accepts file:///, file:/, and file://localhost or this
machine's name, ends the path at '?' or '#', and skips comments, other
schemes, remote hosts, malformed escapes, and escaped NUL bytes. A buffer
that is too small leaves the cursor in place, like the other functions
that fill a buffer.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

1 files changed, 79 insertions, 0 deletions

diff --git a/src/common/uri.c b/src/common/uri.c
new file mode 100644
index 0000000..d836943
--- /dev/null
+++ b/src/common/uri.c
@@ -0,0 +1,79 @@
+#define _POSIX_C_SOURCE 200809L
+#include "yasl/yasl.h"
+
+#include <string.h>
+#include <strings.h>
+#include <unistd.h>
+
+/* decode_path() result for a line that is not a local file URI. */
+#define NOT_LOCAL SIZE_MAX
+
+static int hex_digit(char c)
+{
+    if (c >= '0' && c <= '9') return c - '0';
+    if (c >= 'a' && c <= 'f') return c - 'a' + 10;
+    if (c >= 'A' && c <= 'F') return c - 'A' + 10;
+    return -1;
+}
+
+static bool local_host(const char *host, size_t len)
+{
+    if (len == 9 && strncasecmp(host, "localhost", 9) == 0) return true;
+    char name[256];
+    if (gethostname(name, sizeof(name)) != 0) return false;
+    name[sizeof(name) - 1] = '\0';
+    return strlen(name) == len && strncasecmp(host, name, len) == 0;
+}
+
+/* Decode the path of one uri-list line. Writes to out only when out is not
+ * NULL; the caller checks the length first. */
+static size_t decode_path(const char *line, size_t len, char *out)
+{
+    const char *p = line, *end = line + len;
+    if (len < 5 || strncasecmp(p, "file:", 5) != 0) return NOT_LOCAL;
+    p += 5;
+    if (end - p >= 2 && p[0] == '/' && p[1] == '/') {
+        const char *host = p + 2;
+        p = host;
+        while (p < end && *p != '/') p++;
+        if (p > host && !local_host(host, (size_t)(p - host))) return NOT_LOCAL;
+    }
+    if (p == end || *p != '/') return NOT_LOCAL;
+    size_t n = 0;
+    while (p < end && *p != '?' && *p != '#') {
+        char c = *p++;
+        if (c == '%') {
+            if (end - p < 2) return NOT_LOCAL;
+            int hi = hex_digit(p[0]), lo = hex_digit(p[1]);
+            if (hi < 0 || lo < 0 || (hi == 0 && lo == 0)) return NOT_LOCAL;
+            c = (char)(hi << 4 | lo);
+            p += 2;
+        }
+        if (out) out[n] = c;
+        n++;
+    }
+    return n;
+}
+
+size_t yasl_drop_next_path(const char **cursor, char *out, size_t cap)
+{
+    if (!cursor || !*cursor || (!out && cap)) return 0;
+    const char *p = *cursor;
+    while (*p) {
+        const char *line = p;
+        while (*p && *p != '\r' && *p != '\n') p++;
+        size_t len = (size_t)(p - line);
+        while (*p == '\r' || *p == '\n') p++;
+        while (len && (line[len - 1] == ' ' || line[len - 1] == '\t')) len--;
+        if (!len || line[0] == '#') continue;
+        size_t n = decode_path(line, len, NULL);
+        if (n == NOT_LOCAL) continue;
+        if (n >= cap) return n;
+        decode_path(line, len, out);
+        out[n] = '\0';
+        *cursor = p;
+        return n;
+    }
+    *cursor = p;
+    return 0;
+}