From a74914a05762f03422b492c8d3b2f9e35840708f Mon Sep 17 00:00:00 2001
From: wm4 <wm4@nowhere>
Date: Sat, 1 Aug 2015 23:51:51 +0200
Subject: charset_conv: add uchardet support

For now, it needs to be explicitly selected. ENCA is still the default.

This assumes uchardet returns iconv names. This doesn't seem to be
always the case, and the result are lots of iconv errors. So
explicitly check for this situation, and print a warning if it
occurs. It's entirely possible that uchardet support is actually
useless, because names are not necessarily iconv-compatible (but
uchardet doesn't seem to document whether it attempts to return
iconv-compatible names if possible).

Fixes #908.
---
 DOCS/man/options.rst |  6 ++++++
 TOOLS/old-configure  |  2 ++
 misc/charset_conv.c  | 39 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

diff --git a/DOCS/man/options.rst b/DOCS/man/options.rst
index da40cadb97..72fc74108b 100644
--- a/DOCS/man/options.rst
+++ b/DOCS/man/options.rst
@@ -1491,6 +1491,12 @@ Subtitles
     mode. Use ``--sub-codepage=guess:help`` to get a list of
     languages subject to the same caveat as with ENCA above.
 
+    If the player was compiled with uchardet support you can use it with:
+
+    ``--sub-codepage=uchardet``
+
+    This mode doesn't take language or fallback codepage.
+
 ``--sub-fix-timing``, ``--no-sub-fix-timing``
     By default, external text subtitles are preprocessed to remove minor gaps
     or overlaps between subtitles (if the difference is smaller than 200 ms,
diff --git a/TOOLS/old-configure b/TOOLS/old-configure
index 68805fe331..5751903d95 100755
--- a/TOOLS/old-configure
+++ b/TOOLS/old-configure
@@ -176,6 +176,7 @@ options_state_machine() {
     opt_yes_no _dvdread     "libdvdread"
     opt_yes_no _dvdnav      "libdvdnav"
     opt_yes_no _enca        "ENCA charset oracle library"
+    opt_yes_no _uchardet    "uchardet charset detection library"
     opt_yes_no _libass      "subtitle rendering with libass"
     opt_yes_no _libavdevice "libavdevice demuxers"
     opt_yes_no _libavfilter "libavfilter"
@@ -732,6 +733,7 @@ echo "LIBASS_OSD = $_libass" >> $CONFIG_MAK
 echo "DUMMY_OSD = $_dummy_osd" >> $CONFIG_MAK
 
 check_pkg_config "ENCA" $_enca ENCA 'enca'
+check_pkg_config "uchardet" $_uchardet UCHARDET 'uchardet'
 
 check_pkg_config "zlib" auto ZLIB 'zlib'
 test $(defretval) = no && die "Unable to find development files for zlib."
diff --git a/misc/charset_conv.c b/misc/charset_conv.c
index 343fb7fd90..b96b9bb8c8 100644
--- a/misc/charset_conv.c
+++ b/misc/charset_conv.c
@@ -36,6 +36,10 @@
 #include <libguess.h>
 #endif
 
+#if HAVE_UCHARDET
+#include <uchardet.h>
+#endif
+
 #if HAVE_ICONV
 #include <iconv.h>
 #endif
@@ -81,6 +85,7 @@ bool mp_charset_requires_guess(const char *user_cp)
     // Note that "utf8" is the UTF-8 codepage, while "utf8:..." specifies UTF-8
     // by default, plus a codepage that is used if the input is not UTF-8.
     return bstrcasecmp0(res[0], "enca") == 0 ||
+           bstrcasecmp0(res[0], "uchardet") == 0 ||
            bstrcasecmp0(res[0], "auto") == 0 ||
            bstrcasecmp0(res[0], "guess") == 0 ||
            (r > 1 && bstrcasecmp0(res[0], "utf-8") == 0) ||
@@ -145,6 +150,35 @@ static const char *libguess_guess(struct mp_log *log, bstr buf,
 }
 #endif
 
+#if HAVE_UCHARDET
+static const char *mp_uchardet(void *talloc_ctx, struct mp_log *log, bstr buf)
+{
+    uchardet_t det = uchardet_new();
+    if (!det)
+        return NULL;
+    if (uchardet_handle_data(det, buf.start, buf.len) != 0) {
+        uchardet_delete(det);
+        return NULL;
+    }
+    uchardet_data_end(det);
+    char *res = talloc_strdup(talloc_ctx, uchardet_get_charset(det));
+    if (res && !res[0])
+        res = NULL;
+    if (res) {
+        iconv_t icdsc = iconv_open("UTF-8", res);
+        if (icdsc == (iconv_t)(-1)) {
+            mp_warn(log, "Charset detected as %s, but not supported by iconv.\n",
+                    res);
+            res = NULL;
+        } else {
+            iconv_close(icdsc);
+        }
+    }
+    uchardet_delete(det);
+    return res;
+}
+#endif
+
 // Runs charset auto-detection on the input buffer, and returns the result.
 // If auto-detection fails, NULL is returned.
 // If user_cp doesn't refer to any known auto-detection (for example because
@@ -196,6 +230,11 @@ const char *mp_charset_guess(void *talloc_ctx, struct mp_log *log, bstr buf,
     if (bstrcasecmp0(type, "guess") == 0)
         res = libguess_guess(log, buf, lang);
 #endif
+#if HAVE_UCHARDET
+    if (bstrcasecmp0(type, "uchardet") == 0)
+        res = mp_uchardet(talloc_ctx, log, buf);
+#endif
+
     if (bstrcasecmp0(type, "utf8") == 0 || bstrcasecmp0(type, "utf-8") == 0) {
         if (!fallback)
             fallback = params[1].start; // must be already 0-terminated
-- 
cgit v1.2.3