Fix view-source dpi to handle null characters correctly

Although not allowed in text contexts, null characters should not
stop/halt/fail dpi protocol, thus the patch.

Test Example. Display a file with these contents:

 null padding^@^@

(two trailing null characters)
and view source for it.

Note that dillo will not _display_ the file completely correct,
it will eat a char after each null, but this is not a problem in
dpi nor dpip but in rendering, the cache gets it right.

Adding code to correctly _display_ these anomalous pages is probably
not worth the effort though.

4 files changed, 53 insertions, 30 deletions

diff --git a/doc/Dpid.txt b/doc/Dpid.txt
index 82b81311..6c418f57 100644
--- a/doc/Dpid.txt
+++ b/doc/Dpid.txt
@@ -285,9 +285,10 @@ commented code in hello.c and start making changes!
   Debugging a dpi
   ---------------
 
-  The  simplest  way  is  to add printf() feedback using the MSG*
+  The  simplest way is to add printf-like feedback using the MSG*
 macros.  You  can  start  the dpid by hand on a terminal to force
-messages to go there.
+messages  to  go  there.  Filter  dpis use sdterr and server dpis
+stdout. 
 
   Sometimes  more  complex dpis need more than MSG*. In this case
 you can use gdb like this.
diff --git a/dpi/vsource.c b/dpi/vsource.c
index 2f1129cb..c28e7b49 100644
--- a/dpi/vsource.c
+++ b/dpi/vsource.c
@@ -3,7 +3,7 @@
  *
  * This server is an example. Play with it and modify to your taste.
  *
- * Copyright 2010 Jorge Arellano Cid <jcid@dillo.org>
+ * Copyright 2010-2015 Jorge Arellano Cid <jcid@dillo.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -25,7 +25,7 @@
  * Debugging macros
  */
 #define _MSG(...)
-#define MSG(...)  printf("[vsource dpi]: " __VA_ARGS__)
+#define MSG(...)  fprintf(stderr, "[vsource dpi]: " __VA_ARGS__)
 
 /*---------------------------------------------------------------------------*/
 
@@ -42,38 +42,41 @@ void send_dpip_tag(Dsh *sh, char *dpip_tag)
 
 /*
  * Send source as plain text
+ * (handles embedded null chars correctly).
  */
 void send_plain_text(Dsh *sh, int data_size)
 {
-   int bytes_read = 0;
-   char *src_str;
+   char *token;
+   int bytes_read = 0, token_size;
 
    /* Send HTTP header for plain text MIME type */
    a_Dpip_dsh_write_str(sh, 0, "Content-type: text/plain\n\n");
 
    while (bytes_read < data_size &&
-          (src_str = a_Dpip_dsh_read_token(sh, 1))) {
-      bytes_read += strlen(src_str);
-      a_Dpip_dsh_write_str(sh, 1, src_str);
-      dFree(src_str);
+          (token = a_Dpip_dsh_read_token2(sh, 1, &token_size))) {
+      bytes_read += token_size;
+      _MSG("data_size=%d bytes_read=%d\n", data_size, bytes_read);
+      a_Dpip_dsh_write(sh, 1, token, token_size);
+      dFree(token);
    }
 }
 
 /*
  * Send source as plain text with line numbers
+ * (handles embedded null chars correctly).
  */
 void send_numbered_text(Dsh *sh, int data_size)
 {
-   int bytes_read = 0, line = 1;
-   char *p, *q, *src_str, line_str[32];
+   int bytes_read = 0, line = 1, token_size = 0;
+   char *p, *q, *token, line_str[32];
 
    /* Send HTTP header for plain text MIME type */
    a_Dpip_dsh_write_str(sh, 0, "Content-type: text/plain\n\n");
 
    while (bytes_read < data_size &&
-          (src_str = a_Dpip_dsh_read_token(sh, 1))) {
-      bytes_read += strlen(src_str);
-      p = q = src_str;
+          (token = a_Dpip_dsh_read_token2(sh, 1, &token_size))) {
+      bytes_read += token_size;
+      p = q = token;
 
       while (*p) {
          snprintf(line_str, 32, "%2d: ", line);
@@ -84,28 +87,30 @@ void send_numbered_text(Dsh *sh, int data_size)
                ++p;
             ++line;
          } else {
-            a_Dpip_dsh_write_str(sh, 1, q);
+            /* send all the rest */
+            a_Dpip_dsh_write(sh, 1, q, token_size - (q - token));
             break;
          }
          q = ++p;
       }
-      dFree(src_str);
+      dFree(token);
    }
 }
 
 /*
  * Send source as html text with line numbers
+ * (handles embedded null chars correctly).
  */
 void send_html_text(Dsh *sh, const char *url, int data_size)
 {
-   int bytes_read = 0, old_line = 0, line = 1;
-   char *p, *q, *src_str, line_str[128];
+   int bytes_read = 0, old_line = 0, line = 1, token_size = 0;
+   char *p, *q, *token, line_str[128];
 
    if (dStrnAsciiCasecmp(url, "dpi:", 4) == 0 &&
        strncmp(url+4, "/vsource/:", 10) == 0)
       url += 14;
 
-   /* Send HTTP header for plain text MIME type */
+   /* Send HTTP header for html text MIME type */
    a_Dpip_dsh_write_str(sh, 0, "Content-type: text/html\n\n");
 
    a_Dpip_dsh_write_str(sh, 0, DOCTYPE);
@@ -119,9 +124,9 @@ void send_html_text(Dsh *sh, const char *url, int data_size)
                      "<body id=\"dillo_vs\">\n<table cellpadding='0'>\n", url);
 
    while (bytes_read < data_size &&
-          (src_str = a_Dpip_dsh_read_token(sh, 1))) {
-      bytes_read += strlen(src_str);
-      p = q = src_str;
+          (token = a_Dpip_dsh_read_token2(sh, 1, &token_size))) {
+      bytes_read += token_size;
+      p = q = token;
 
       while (*p) {
          if (line > old_line) {
@@ -143,13 +148,14 @@ void send_html_text(Dsh *sh, const char *url, int data_size)
                a_Dpip_dsh_write(sh, 0, q, p - q);
                a_Dpip_dsh_write_str(sh, 0, (*p == '<') ? "&lt;" : "&amp;");
             }
-         } else {
-            a_Dpip_dsh_write_str(sh, 1, q);
+         } else { 
+            /* send all the rest */
+            a_Dpip_dsh_write(sh, 1, q, token_size - (q - token));
             break;
          }
          q = ++p;
       }
-      dFree(src_str);
+      dFree(token);
    }
 
    if (data_size > 0)
@@ -194,7 +200,7 @@ int main(void)
     * asking from us. a_Dpip_dsh_read_token() will block and return
     * a full dpip token or null on error (it's commented in dpip.c) */
    dpip_tag = a_Dpip_dsh_read_token(sh, 1);
-   MSG("tag = [%s]\n", dpip_tag);
+   _MSG("tag = [%s]\n", dpip_tag);
 
    /* Now that we have the dpip_tag, let's isolate the command and url */
    cmd = a_Dpip_get_attr(dpip_tag, "cmd");
diff --git a/dpip/dpip.c b/dpip/dpip.c
index f4ce1bf0..2906ba2a 100644
--- a/dpip/dpip.c
+++ b/dpip/dpip.c
@@ -1,7 +1,7 @@
 /*
  * File: dpip.c
  *
- * Copyright 2005-2007 Jorge Arellano Cid <jcid@dillo.org>
+ * Copyright 2005-2015 Jorge Arellano Cid <jcid@dillo.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -427,11 +427,13 @@ static void Dpip_dsh_read(Dsh *dsh, int blocking)
 
 /*
  * Return a newlly allocated string with the next dpip token in the socket.
- * Return value: token string on success, NULL otherwise
+ * Return value: token string and length on success, NULL otherwise.
+ * (useful for handling null characters in the data stream)
  */
-char *a_Dpip_dsh_read_token(Dsh *dsh, int blocking)
+char *a_Dpip_dsh_read_token2(Dsh *dsh, int blocking, int *DataSize)
 {
    char *p, *ret = NULL;
+   *DataSize = 0;
 
    /* Read all available data without blocking */
    Dpip_dsh_read(dsh, 0);
@@ -462,6 +464,7 @@ char *a_Dpip_dsh_read_token(Dsh *dsh, int blocking)
       /* return a full tag */
       if ((p = strstr(dsh->rdbuf->str, DPIP_TAG_END))) {
          ret = dStrndup(dsh->rdbuf->str, p - dsh->rdbuf->str + 3);
+         *DataSize = p - dsh->rdbuf->str + 3;
          dStr_erase(dsh->rdbuf, 0, p - dsh->rdbuf->str + 3);
          if (strstr(ret, DPIP_MODE_SWITCH_TAG))
             dsh->mode |= DPIP_LAST_TAG;
@@ -470,6 +473,7 @@ char *a_Dpip_dsh_read_token(Dsh *dsh, int blocking)
       /* raw mode, return what we have "as is" */
       if (dsh->rdbuf->len > 0) {
          ret = dStrndup(dsh->rdbuf->str, dsh->rdbuf->len);
+         *DataSize = dsh->rdbuf->len;
          dStr_truncate(dsh->rdbuf, 0);
       }
    }
@@ -478,6 +482,17 @@ char *a_Dpip_dsh_read_token(Dsh *dsh, int blocking)
 }
 
 /*
+ * Return a newlly allocated string with the next dpip token in the socket.
+ * Return value: token string on success, NULL otherwise
+ */
+char *a_Dpip_dsh_read_token(Dsh *dsh, int blocking)
+{
+   int token_size;
+
+   return a_Dpip_dsh_read_token2(dsh, blocking, &token_size);
+}
+
+/*
  * Close this socket for reading and writing.
  * (flush pending data)
  */
diff --git a/dpip/dpip.h b/dpip/dpip.h
index 1a1846df..a63eb658 100644
--- a/dpip/dpip.h
+++ b/dpip/dpip.h
@@ -70,6 +70,7 @@ int a_Dpip_dsh_write_str(Dsh *dsh, int flush, const char *str);
 int a_Dpip_dsh_tryflush(Dsh *dsh);
 int a_Dpip_dsh_trywrite(Dsh *dsh, const char *Data, int DataSize);
 char *a_Dpip_dsh_read_token(Dsh *dsh, int blocking);
+char *a_Dpip_dsh_read_token2(Dsh *dsh, int blocking, int *DataSize);
 void a_Dpip_dsh_close(Dsh *dsh);
 void a_Dpip_dsh_free(Dsh *dsh);