Source Format Enforcement (#532)

[thirdparty/squid.git] / src / http / one / Tokenizer.h

diff --git a/src/http/one/Tokenizer.h b/src/http/one/Tokenizer.h
index a29ce5c5d1cc5e696a1273f9456b1c8a59c38e29..c4764bdc19728693295e08fbd62729b2f77235e5 100644 (file)
--- a/src/http/one/Tokenizer.h
+++ b/src/http/one/Tokenizer.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 1996-2019 The Squid Software Foundation and contributors
+ * Copyright (C) 1996-2020 The Squid Software Foundation and contributors
  *
  * Squid software is distributed under GPLv2+ license and includes
  * contributions from numerous individuals and organizations.
@@ -9,68 +9,47 @@
 #ifndef SQUID_SRC_HTTP_ONE_TOKENIZER_H
 #define SQUID_SRC_HTTP_ONE_TOKENIZER_H
 
-#include "parser/Tokenizer.h"
+#include "parser/forward.h"
+#include "sbuf/forward.h"
 
 namespace Http {
 namespace One {
 
 /**
- * Lexical processor extended to tokenize HTTP/1.x syntax.
+ * Extracts either an HTTP/1 token or quoted-string while dealing with
+ * possibly incomplete input typical for incremental text parsers.
+ * Unescapes escaped characters in HTTP/1.1 quoted strings.
  *
- * \see ::Parser::Tokenizer for more detail
+ * \param http1p0 whether to prohibit \-escaped characters in quoted strings
+ * \throws InsufficientInput as appropriate, including on unterminated tokens
+ * \returns extracted token or quoted string (without quotes)
+ *
+ * Governed by:
+ *  - RFC 1945 section 2.1
+ *  "
+ *    A string of text is parsed as a single word if it is quoted using
+ *    double-quote marks.
+ *
+ *        quoted-string  = ( <"> *(qdtext) <"> )
+ *
+ *        qdtext         = <any CHAR except <"> and CTLs,
+ *                         but including LWS>
+ *
+ *    Single-character quoting using the backslash ("\") character is not
+ *    permitted in HTTP/1.0.
+ *  "
+ *
+ *  - RFC 7230 section 3.2.6
+ *  "
+ *    A string of text is parsed as a single value if it is quoted using
+ *    double-quote marks.
+ *
+ *    quoted-string  = DQUOTE *( qdtext / quoted-pair ) DQUOTE
+ *    qdtext         = HTAB / SP /%x21 / %x23-5B / %x5D-7E / obs-text
+ *    obs-text       = %x80-FF
+ *  "
  */
-class Tokenizer : public ::Parser::Tokenizer
-{
-public:
-    Tokenizer(SBuf &s) : ::Parser::Tokenizer(s), savedStats_(0) {}
-
-    /**
-     * Attempt to parse a quoted-string lexical construct.
-     *
-     * Governed by:
-     *  - RFC 1945 section 2.1
-     *  "
-     *    A string of text is parsed as a single word if it is quoted using
-     *    double-quote marks.
-     *
-     *        quoted-string  = ( <"> *(qdtext) <"> )
-     *
-     *        qdtext         = <any CHAR except <"> and CTLs,
-     *                         but including LWS>
-     *
-     *    Single-character quoting using the backslash ("\") character is not
-     *    permitted in HTTP/1.0.
-     *  "
-     *
-     *  - RFC 7230 section 3.2.6
-     *  "
-     *    A string of text is parsed as a single value if it is quoted using
-     *    double-quote marks.
-     *
-     *    quoted-string  = DQUOTE *( qdtext / quoted-pair ) DQUOTE
-     *    qdtext         = HTAB / SP /%x21 / %x23-5B / %x5D-7E / obs-text
-     *    obs-text       = %x80-FF
-     *  "
-     *
-     * \param escaped HTTP/1.0 does not permit \-escaped characters
-     */
-    bool quotedString(SBuf &value, const bool http1p0 = false);
-
-    /**
-     * Attempt to parse a (token / quoted-string ) lexical construct.
-     */
-    bool quotedStringOrToken(SBuf &value, const bool http1p0 = false);
-
-private:
-    /// parse the internal component of a quote-string, and terminal DQUOTE
-    bool qdText(SBuf &value, const bool http1p0);
-
-    void checkpoint() { savedCheckpoint_ = buf(); savedStats_ = parsedSize(); }
-    void restoreLastCheckpoint() { undoParse(savedCheckpoint_, savedStats_); }
-
-    SBuf savedCheckpoint_;
-    SBuf::size_type savedStats_;
-};
+SBuf tokenOrQuotedString(Parser::Tokenizer &tok, const bool http1p0 = false);
 
 } // namespace One
 } // namespace Http