summaryrefslogtreecommitdiffstats
path: root/src/global/header_token.c
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-06 01:46:30 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-06 01:46:30 +0000
commitb5896ba9f6047e7031e2bdee0622d543e11a6734 (patch)
treefd7b460593a2fee1be579bec5697e6d887ea3421 /src/global/header_token.c
parentInitial commit. (diff)
downloadpostfix-b5896ba9f6047e7031e2bdee0622d543e11a6734.tar.xz
postfix-b5896ba9f6047e7031e2bdee0622d543e11a6734.zip
Adding upstream version 3.4.23.upstream/3.4.23upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'src/global/header_token.c')
-rw-r--r--src/global/header_token.c266
1 files changed, 266 insertions, 0 deletions
diff --git a/src/global/header_token.c b/src/global/header_token.c
new file mode 100644
index 0000000..3375125
--- /dev/null
+++ b/src/global/header_token.c
@@ -0,0 +1,266 @@
+/*++
+/* NAME
+/* header_token 3
+/* SUMMARY
+/* mail header parser
+/* SYNOPSIS
+/* #include <header_token.h>
+/*
+/* typedef struct {
+/* .in +4
+/* int type;
+/* const char *u.value;
+/* /* ... */
+/* .in
+/* } HEADER_TOKEN;
+/*
+/* ssize_t header_token(token, token_len, token_buffer, ptr,
+/* specials, terminator)
+/* HEADER_TOKEN *token;
+/* ssize_t token_len;
+/* VSTRING *token_buffer;
+/* const char **ptr;
+/* const char *specials;
+/* int terminator;
+/* DESCRIPTION
+/* This module parses a mail header value (text after field-name:)
+/* into tokens. The parser understands RFC 822 linear white space,
+/* quoted-string, comment, control characters, and a set of
+/* user-specified special characters.
+/*
+/* A result token type is one of the following:
+/* .IP HEADER_TOK_QSTRING
+/* Quoted string as per RFC 822.
+/* .IP HEADER_TOK_TOKEN
+/* Token as per RFC 822, and the special characters supplied by the
+/* caller.
+/* .IP other
+/* The value of a control character or special character.
+/* .PP
+/* header_token() tokenizes the input and stops after a user-specified
+/* terminator (ignoring all tokens that exceed the capacity of
+/* the result storage), or when it runs out of space for the result.
+/* The terminator is not stored. The result value is the number of
+/* tokens stored, or -1 when the input was exhausted before any tokens
+/* were found.
+/*
+/* Arguments:
+/* .IP token
+/* Result array of HEADER_TOKEN structures. Token string values
+/* are pointers to null-terminated substrings in the token_buffer.
+/* .IP token_len
+/* Length of the array of HEADER_TOKEN structures.
+/* .IP token_buffer
+/* Storage for result token string values.
+/* .IP ptr
+/* Input/output read position. The input is a null-terminated string.
+/* .IP specials
+/* Special characters according to the relevant RFC, or a
+/* null pointer (default to the RFC 822 special characters).
+/* This must include the optional terminator if one is specified.
+/* .IP terminator
+/* The special character to stop after, or zero.
+/* BUGS
+/* Eight-bit characters are not given special treatment.
+/* SEE ALSO
+/* RFC 822 (ARPA Internet Text Messages)
+/* DIAGNOSTICS
+/* Fatal errors: memory allocation problem.
+/* LICENSE
+/* .ad
+/* .fi
+/* The Secure Mailer license must be distributed with this software.
+/* AUTHOR(S)
+/* Wietse Venema
+/* IBM T.J. Watson Research
+/* P.O. Box 704
+/* Yorktown Heights, NY 10598, USA
+/*--*/
+
+/* System library. */
+
+#include <sys_defs.h>
+#include <string.h>
+#include <ctype.h>
+
+/* Utility library. */
+
+#include <msg.h>
+#include <vstring.h>
+
+/* Global library. */
+
+#include <lex_822.h>
+#include <header_token.h>
+
+/* Application-specific. */
+
+ /*
+ * Silly little macros.
+ */
+#define STR(x) vstring_str(x)
+#define LEN(x) VSTRING_LEN(x)
+#define CU_CHAR_PTR(x) ((const unsigned char *) (x))
+
+/* header_token - parse out the next item in a message header */
+
+ssize_t header_token(HEADER_TOKEN *token, ssize_t token_len,
+ VSTRING *token_buffer, const char **ptr,
+ const char *user_specials, int user_terminator)
+{
+ ssize_t comment_level;
+ const unsigned char *cp;
+ ssize_t len;
+ int ch;
+ ssize_t tok_count;
+ ssize_t n;
+
+ /*
+ * Initialize.
+ */
+ VSTRING_RESET(token_buffer);
+ cp = CU_CHAR_PTR(*ptr);
+ tok_count = 0;
+ if (user_specials == 0)
+ user_specials = LEX_822_SPECIALS;
+
+ /*
+ * Main parsing loop.
+ *
+ * XXX What was the reason to continue parsing when user_terminator is
+ * specified? Perhaps this was needed at some intermediate stage of
+ * development?
+ */
+ while ((ch = *cp) != 0 && (user_terminator != 0 || tok_count < token_len)) {
+ cp++;
+
+ /*
+ * Skip RFC 822 linear white space.
+ */
+ if (IS_SPACE_TAB_CR_LF(ch))
+ continue;
+
+ /*
+ * Terminator.
+ */
+ if (ch == user_terminator)
+ break;
+
+ /*
+ * Skip RFC 822 comment.
+ */
+ if (ch == '(') {
+ comment_level = 1;
+ while ((ch = *cp) != 0) {
+ cp++;
+ if (ch == '(') { /* comments can nest! */
+ comment_level++;
+ } else if (ch == ')') {
+ if (--comment_level == 0)
+ break;
+ } else if (ch == '\\') {
+ if ((ch = *cp) == 0)
+ break;
+ cp++;
+ }
+ }
+ continue;
+ }
+
+ /*
+ * Copy quoted text according to RFC 822.
+ */
+ if (ch == '"') {
+ if (tok_count < token_len) {
+ token[tok_count].u.offset = LEN(token_buffer);
+ token[tok_count].type = HEADER_TOK_QSTRING;
+ }
+ while ((ch = *cp) != 0) {
+ cp++;
+ if (ch == '"')
+ break;
+ if (ch == '\n') { /* unfold */
+ if (tok_count < token_len) {
+ len = LEN(token_buffer);
+ while (len > 0
+ && IS_SPACE_TAB_CR_LF(STR(token_buffer)[len - 1]))
+ len--;
+ if (len < LEN(token_buffer))
+ vstring_truncate(token_buffer, len);
+ }
+ continue;
+ }
+ if (ch == '\\') {
+ if ((ch = *cp) == 0)
+ break;
+ cp++;
+ }
+ if (tok_count < token_len)
+ VSTRING_ADDCH(token_buffer, ch);
+ }
+ if (tok_count < token_len) {
+ VSTRING_ADDCH(token_buffer, 0);
+ tok_count++;
+ }
+ continue;
+ }
+
+ /*
+ * Control, or special.
+ */
+ if (strchr(user_specials, ch) || ISCNTRL(ch)) {
+ if (tok_count < token_len) {
+ token[tok_count].u.offset = LEN(token_buffer);
+ token[tok_count].type = ch;
+ VSTRING_ADDCH(token_buffer, ch);
+ VSTRING_ADDCH(token_buffer, 0);
+ tok_count++;
+ }
+ continue;
+ }
+
+ /*
+ * Token.
+ */
+ else {
+ if (tok_count < token_len) {
+ token[tok_count].u.offset = LEN(token_buffer);
+ token[tok_count].type = HEADER_TOK_TOKEN;
+ VSTRING_ADDCH(token_buffer, ch);
+ }
+ while ((ch = *cp) != 0 && !IS_SPACE_TAB_CR_LF(ch)
+ && !ISCNTRL(ch) && !strchr(user_specials, ch)) {
+ cp++;
+ if (tok_count < token_len)
+ VSTRING_ADDCH(token_buffer, ch);
+ }
+ if (tok_count < token_len) {
+ VSTRING_ADDCH(token_buffer, 0);
+ tok_count++;
+ }
+ continue;
+ }
+ }
+
+ /*
+ * Ignore a zero-length item after the last terminator.
+ */
+ if (tok_count == 0 && ch == 0)
+ return (-1);
+
+ /*
+ * Finalize. Fill in the string pointer array, now that the token buffer
+ * is no longer dynamically reallocated as it grows.
+ */
+ *ptr = (const char *) cp;
+ for (n = 0; n < tok_count; n++)
+ token[n].u.value = STR(token_buffer) + token[n].u.offset;
+
+ if (msg_verbose)
+ msg_info("header_token: %s %s %s",
+ tok_count > 0 ? token[0].u.value : "",
+ tok_count > 1 ? token[1].u.value : "",
+ tok_count > 2 ? token[2].u.value : "");
+
+ return (tok_count);
+}