From 211563241b92dc518e179c461326a1bef2ba835f Mon Sep 17 00:00:00 2001
From: Robert Smith <robert@rigetti.com>
Date: Sat, 4 Aug 2018 19:58:24 -0700
Subject: add internal control *LOOK-AHEAD-FOR-SUFFIX*

This allows better performance for some scanning use-cases.

We also bump the minor version to 2.1.0.
---
 api.lisp        |  7 ++++++-
 cl-ppcre.asd    |  2 +-
 docs/index.html | 26 ++++++++++++++++++++++++++
 packages.lisp   |  1 +
 4 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/api.lisp b/api.lisp
index 4c11c45..f440361 100644
--- a/api.lisp
+++ b/api.lisp
@@ -31,6 +31,10 @@
 
 (in-package :cl-ppcre)
 
+(defvar *look-ahead-for-suffix* t
+  "Controls whether scanners will optimistically look ahead for a
+  constant suffix of a regular expression, if there is one.")
+
 (defgeneric create-scanner (regex &key case-insensitive-mode
                                        multi-line-mode
                                        single-line-mode
@@ -120,7 +124,8 @@ modify its first argument \(but only if it's a parse tree)."))
                (end-string (end-string regex))
                ;; if we found a non-zero-length end-string we create an
                ;; efficient search function for it
-               (end-string-test (and end-string
+               (end-string-test (and *look-ahead-for-suffix*
+                                     end-string
                                      (plusp (len end-string))
                                      (if (= 1 (len end-string))
                                        (create-char-searcher
diff --git a/cl-ppcre.asd b/cl-ppcre.asd
index b1e3547..f1c83af 100644
--- a/cl-ppcre.asd
+++ b/cl-ppcre.asd
@@ -37,7 +37,7 @@
 (in-package :cl-ppcre-asd)
 
 (defsystem :cl-ppcre
-  :version "2.0.11"
+  :version "2.1.0"
   :description "Perl-compatible regular expression library"
   :author "Dr. Edi Weitz"
   :license "BSD"
diff --git a/docs/index.html b/docs/index.html
index 4cd0d91..6da6a15 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -103,6 +103,7 @@ href="http://weitz.de/regex-coach/">The Regex Coach</a>.
       <li><a href="#*optimize-char-classes*"><code>*optimize-char-classes*</code></a>
       <li><a href="#*allow-quoting*"><code>*allow-quoting*</code></a>
       <li><a href="#*allow-named-registers*"><code>*allow-named-registers*</code></a>
+      <li><a href="#*look-ahead-for-suffix*"><code>*look-ahead-for-suffix*</code></a>
     </ol>
     <li><a href="#misc">Miscellaneous</a>
     <ol>
@@ -1391,6 +1392,31 @@ to which value <code>*ALLOW-NAMED-REGISTERS*</code> is bound at that
 time.</blockquote>
 </blockquote>
 
+<p><br>[Special variable]
+<br><a class=none name="*look-ahead-for-suffix*"><b>*look-ahead-for-suffix*</b></a>
+
+<blockquote><br>Given a regular expression which has a constant
+suffix, such as <code>(a|b)+x</code> whose constant suffix
+is <code>x</code>, the scanners created
+by <a href="#create-scanner"><code>CREATE-SCANNER</code></a> will
+attempt to optimize by searching for the position of the suffix prior
+to performing the full match. In many cases, this is an optimization,
+especially when backtracking is involved on small strings. However, in
+other cases, such as incremental parsing of a very large string, this
+can cause a degradation in performance, because the entire string is
+searched for the suffix before an otherwise easy prefix match failure
+can occur. The variable <code>*LOOK-AHEAD-FOR-SUFFIX*</code>, whose
+default is <code>T</code>, can be used to selectively control this
+behavior.
+<p>
+Note: Due to the nature of <a href="http://www.lispworks.com/documentation/HyperSpec/Body/s_ld_tim.htm"><code>LOAD-TIME-VALUE</code></a> and the <a
+href="#compiler-macro">compiler macro for <code>SCAN</code> and other functions</a>, some
+scanners might be created in a <a
+href="http://www.lispworks.com/documentation/HyperSpec/Body/26_glo_n.htm#null_lexical_environment">null
+lexical environment</a> at load time or at compile time so be careful
+to which value <code>*LOOK-AHEAD-FOR-SUFFIX*</code> is bound at that
+time.</blockquote>
+
 <h4><a name="misc" class=none>Miscellaneous</a></h4>
 
 <p><br>[Function]
diff --git a/packages.lisp b/packages.lisp
index bfb10d1..74faa44 100644
--- a/packages.lisp
+++ b/packages.lisp
@@ -59,6 +59,7 @@
            :*allow-named-registers*
            :*optimize-char-classes*
            :*property-resolver*
+           :*look-ahead-for-suffix*
            :ppcre-error
            :ppcre-invocation-error
            :ppcre-syntax-error
-- 
cgit v1.2.3-70-g09d2