[ptime] fix non-english month abbrev handling

Author: tstack

src/ptimec.hh

@@ -65,7 +65,7 @@
     dst[off_inout] = ch; \
     off_inout += 1;
 
-#define ABR_TO_INT(a, b, c) (((a) << 24) | ((b) << 16) | ((c) << 8))
+#define ABR_TO_INT(a, b, c)     (((a) << 24) | ((b) << 16) | ((c) << 8))
 #define ABR_TO_INT4(a, b, c, d) (((a) << 24) | ((b) << 16) | ((c) << 8) | ((d)))
 
 inline bool
@@ -153,7 +153,9 @@ ptime_b_int(struct exttm* dst, const char* str, off_t off)
 }
 
 #define PTIME_CHECK_b(dst, str, off) \
-    if (!ptime_b_int(dst, str, off)) { \
+    if (str[off + 3] == '.' || isalpha(str[off + 3]) \
+        || !ptime_b_int(dst, str, off)) \
+    { \
         off_t tmp_off = off; \
         if (!ptime_b_slow(dst, str, tmp_off, len)) { \
             off_inout = off; \
@@ -166,7 +168,17 @@ ptime_b_int(struct exttm* dst, const char* str, off_t off)
 inline bool
 ptime_b(exttm* dst, const char* str, off_t& off_inout, ssize_t len)
 {
-    if (off_inout + 3 < len) {
+    // fast path to detect english abbreviated months
+    //
+    // only detect english abbreviated months if they end at a word
+    // boundary. if the abbreviated month in the current locale is longer
+    // than 3 letters, and starts with the same letters as an english locale
+    // month abbreviation, then the computation of off_inout is incorrect.
+    //
+    // Ex: in fr_FR november is `nov.`. Parsing `nov. 29` as `%b %d` fails
+    // if this fast path is taken as later we will attempt to parse `. 29`
+    // as ` %d`.
+    if (off_inout + 3 < len && isspace(str[off_inout + 3])) {
         if (ptime_b_int(dst, str, off_inout)) {
             off_inout += 3;
             return true;

src/ptimec_rt.cc

@@ -48,6 +48,12 @@ ptime_b_slow(struct exttm* dst, const char* str, off_t& off_inout, ssize_t len)
     zone[zone_len] = '\0';
     if ((end_of_date = strptime(zone, "%b", &dst->et_tm)) != NULL) {
         off_inout += end_of_date - zone;
+        // Some formats append a dot, maybe to align a 3 letter abbrev with the
+        // four letter ones?
+        if (off_inout + 1 < len && zone[off_inout] == '.') {
+            off_inout += 1;
+        }
+        dst->et_flags |= ETF_MONTH_SET;
         return true;
     }
 

test/test_date_time_scanner.cc

@@ -231,6 +231,7 @@ TEST_CASE("date_time_scanner")
     {
         const char* en_date = "Jan  1 12:00:00";
         const char* fr_date = "août 19 11:08:37";
+        const char* fr_date2 = "nov. 29 20:23:37";
         timeval en_tv, fr_tv;
         exttm en_tm, fr_tm;
         date_time_scanner dts;
@@ -241,6 +242,9 @@ TEST_CASE("date_time_scanner")
             dts.clear();
             CHECK(dts.scan(fr_date, strlen(fr_date), nullptr, &fr_tm, fr_tv)
                   != nullptr);
+            dts.clear();
+            assert(dts.scan(fr_date2, strlen(fr_date), nullptr, &fr_tm, fr_tv)
+                   != nullptr);
         }
     }