Changes

Revision history for Perl extension RiveScript.

  2.0.4  Nov 25 2022
  - Fix certain combinations of nested tags causing an infinite loop to
    parse them.
  - Fix {weight} tags in triggers not trimming remaining whitespace after
    they are removed, which affected trigger matching ability.

  2.0.3  Aug 26 2016
  - Fix inline comment regexp that was making URLs impossible to represent
    in replies.

  2.0.2  Jan 11 2016
  - Fix typo in changelog.

  2.0.1  Jan 11 2016
  - When formatting a user's message, consolidate multiple consecutive spaces
    down to one.
  - Apply downstream Debian patch that fixes a typo in RiveScript::WD.

  2.0.0  Dec 28 2015
  - Switch from old-style floating point version number notation to dotted
    decimal notation. This bumps the version number to `2.0.0` because the next
    dotted-decimal version greater than `1.42` (`v1.420.0`) is `v1.421.0` and
    I don't like having that many digits in the version number. This release is
    simply a version update; no breaking API changes were introduced.

  1.42  Nov 20 2015
  - Add configurable `unicode_punctuation` attribute to strip out punctuation
    when running in UTF-8 mode.

  1.40  Oct 10 2015
  - Fix the regexp used when matching optionals so that the triggers don't match
    on inputs where they shouldn't. (RiveScript-JS issue #46)

  1.38  Jul 21 2015
  - New algorithm for handling variable tags (<get>, <set>, <add>, <sub>,
    <mult>, <div>, <bot> and <env>) that allows for iterative nesting of these
    tags (for example, <set copy=<get orig>> will work now).
  - Fix trigger sorting so that triggers with matching word counts are sorted
    by length descending.
  - Add support for `! local concat` option to override concatenation mode
    (file scoped)
  - Bugfix where Perl object macros set via `setSubroutine()` failed to load
    because they were missing a programming language internally.

  1.36  Nov 26 2014
  - Relicense under the MIT License.
  - Strip punctuation from the bot's responses in UTF-8 mode to
    support compatibility with %Previous.
  - Bugfix in deparse(): If you had two matching triggers, one with a %Previous
    and one without, you'd lose the data for one of them in the output.

  1.34  Feb 26 2014
  - Update README.md to include module documentation for github.
  - Fixes to META.yml

  1.32  Feb 24 2014
  - Maintenance release to fix some errors per the CPANTS.
  - Add license to Makefile.PL
  - Make Makefile.PL not executable
  - Make version numbers consistent

  1.30  Nov 25 2013
  - Added "TCP Mode" to the `rivescript` command so that it can listen on a
    socket instead of using standard input and output.
  - Added a "--data" option to the `rivescript` command for providing JSON
    input as a command line argument instead of standard input.
  - Added experimental UTF-8 support.
  - Bugfix: don't use hacky ROT13-encoded placeholders for message
    substitutions... use a null character method instead. ;)
  - Make .rive the default preferred file extension for RiveScript documents
    instead of .rs (which conflicts with the Rust programming language).
    Backwards compatibility remains to load .rs files, though.

  1.28  Aug 14 2012
  - FIXED: Typos in RiveScript::WD (Bug #77618)
  - Added constants RS_ERR_MATCH and RS_ERR_REPLY.

  1.26  May 29 2012
  - Added EXE_FILES to Makefile.PL so the rivescript utility installs
    correctly.

  1.24  May 15 2012
  - Fixed: having a single-line, multiline comment, e.g. /* ... */
  - Fixed: you can use <input> and <reply> in triggers now, instead of only
    <input1>-<input9> and <reply1>-<reply9>
  - When a trigger consists of nothing but multiple wildcard symbols, sort
    the trigger by length, this way you can have '* * * * *' type triggers
    still work correctly (each <star> tag would get one word, with the final
    <star> collecting the remainder).
  - Backported new feature from Python lib: you can now use <bot> and <env>
    to SET variables (eg. <bot mood=happy>). The {!...} tag is deprecated.
  - New feature: deparse() will return a Perl data structure representing all
    of the RiveScript code parsed by the module so far. This way you can build
    a user interface for editing replies without requiring a user to edit the
    code directly.
  - New method: write() will use deparse() to write a RiveScript document using
    all of the in-memory triggers/responses/etc.
  - Cleaned up the POD documentation, put POD code along side the Perl functions
    it documents, removed useless bloat from the docs.
  - POD documentation now only shows recent changes. For older changes, see the
    "CHANGES" file in the distribution.
  - Removed the `rsup` script from the distribution (it upgrades RiveScript 1.x
    code to 2.x; there probably isn't any 1.x code out in the wild anyway).

  1.22  Sep 22 2011
  - Cleaned up the documentation of RiveScript; moved the JavaScript object
    example to a separate document in the `docs' directory.
  - Obsoleted the `rsdemo` command that used to ship with the distribution. In
    its place is `rivescript`, which can also be used non-interactively so that a
    third party, non-Perl application could still make use of RiveScript.
  - RiveScript.pm is now dual licensed. It uses the GPLv2 for open source
    applications as before, but you can contact the author for details if you
    want to use RiveScript.pm in a closed source commercial application.

  1.20  Jul 30 2009
  - Added automatic syntax checking when parsing RiveScript code. Also added
    'strict mode' - if true (default), a syntax error is a fatal error. If false,
    a syntax error is a warning, and RiveScript aborts processing the file any
    further.
  - Changed the behavior of "inherits" a bit: a new type has been added called
    "includes" which does what the old "inherits" does (mixes the trigger list
    of both topics together into the same pool). The new "inherits" option though
    causes the trigger list from the source topic to be higher in matching priority
    than the trigger list of the inherited topic.
  - Moving to a new versioning scheme: development releases will have odd
    version numbers, stable (CPAN) versions will have even numbers.
  - Fixed the Eliza brain; in many places a <star2> was used when there was only one
    star in the trigger. Fixes lots of issues with Eliza.
  - Bugfix: recursion depth limits weren't taken into account when the {@} tag
    was responsible for a redirection. Fixed.
  - Bugfix: there was a problem in the regular expression that counts real words
    while sorting triggers, so that triggers with *'s in them weren't sorted
    properly and would therefore cause matching issues.
  - Bugfix: when the internal _getreply is called because of a recursive
    redirection (@, {@}), the %previous tags should be ignored. They weren't.
    since "lastreply" is always the same no matter how deeply recursive _getreply
    is going, it could result in some infinite recursion in rare cases. Fixed.
  - Bugfix: using a reserved name as a global variable wasn't working properly
    and would crash RiveScript. Fixed.

  1.19  Apr 12 2009
  - Added support for defining custom object handlers for non-Perl programming
    languages.
  - All the methods like setGlobal, setVariable, setUservar, etc. will now
    accept undef or "<undef>" as values - this will delete the variables.
  - There are no reserved global variable names anymore. Now, if a variable name
    would conflict with a reserved name, it is put into a "protected" space
    elsewhere in the object. Still take note of which names are reserved though.

  1.18  Dec 31 2008
  - Added support for topics to inherit their triggers from other topics.
    e.g. > topic alpha inherits beta
  - Fixed some bugs related to !array with ^continue's, and expanded its
    functionality therein.
  - Updated the getUservars() function to optionally be able to get just a specific
    variable from the user's data. Added getUservar() as a grammatically correct
    alias to this new functionality.
  - Added the functions freezeUservars() and thawUservars() to back up and
    restore a user's variables.
  - Added the function lastMatch(), which returns the text of the trigger that
    matched the user's last message.
  - The # command for RiveScript comments has been deprecated in revision 7 of
    the RiveScript Working Draft. The Perl module will now emit warnings each
    time the # comments are processed.
  - Modified a couple of triggers in the default Eliza brain to improve matching
    issues therein.
  - +Triggers can contain user <get> tags now.
  - Updated the RiveScript Working Draft.

  1.17  Sep 15 2008
  - Updated the rsdemo tool to be more flexible as a general debugging and
    developing program. Also updated rsdemo and rsup to include POD documentation
    that can be read via `perldoc`.
  - Added a global variable $RiveScript::basedir which is the the path to your
    Perl lib/RiveScript folder. This is used by `rsdemo` as its default location
    to search for replies.
  - Tweak: Triggers of only # and _ can exist now alongside the old single-wildcard
    trigger of *.
  - Bugfix: The lookahead code would throw Perl warnings if the following line
    had a single space in it, but was otherwise empty.
  - Bugfix: Inline comment removing has been fixed.
  - Bugfix: In conditionals, any blank side of the equality will get a default
    value of "undefined". This way you can use a matching array inside an optional
    and check if that <star> tag is defined.
    + i am wearing a [(@colors)] shirt
    * <star> ne undefined => Why are you wearing a <star> shirt?
    - What color is it?
  - Updated the RiveScript Working Draft.

  1.16  Jul 22 2008
  - New options to the constructor: 'verbose' and 'debugfile'. See the new()
    constructor for details.
  - Added new wildcard variants:
    * matches anything (previous behavior)
    # matches only numbers
    _ matches only letters
    So you can have a trigger like "+ i am # years old" and "+ i am * years old",
    with the latter trigger telling them to try that again and use a NUMBER this
    time. :)
  - Bugfix: when there were multiple +trigger's that had a common %previous,
    there was no internal sort buffer for those +trigger's. As a result, matching
    wasn't very efficient. Added the method sortThatTriggers() to fix this.
  - Bugfix: tags weren't being processed in @Redirects when they really
    should've!
  - Bugfix: The ^Continue lookahead code wouldn't work if the next line began
    with a tab. Fixed!
  - Updated the RiveScript Working Draft.

  1.15  Jun 19 2008
  - Person substitutions support multiple-word patterns now.
  - Message substititons also support multiple-word patterns now.
  - Added syntax tracking, so Deep Recursion errors can give you a filename and
    line number where the problem occurred.
  - Added a handler for detecting when a user was put into an empty topic.
  - Rearranged tag priority.
  - Updated the RiveScript Working Draft.

  1.14  Apr  2 2008
  - Bugfix: If a BEGIN/request trigger didn't exist, RiveScript would not fetch
    any replies for the client's message. Fixed.
  - Bugfix: Tags weren't being re-processed for the text of the BEGIN statement,
    so i.e. {uppercase}{ok}{/uppercase} wasn't working as expected. Fixed.
  - Bugfix: RiveScript wasn't parsing out inline comments properly.
  - Rearranged tag priorities.
  - Optimization: When substituting <star>s in, an added bit of code will insert
    '' (nothing) if the variable is undefined. This prevents Perl warnings that
    occurred frequently with the Eliza brain.
  - Updated the RiveScript Working Draft.

  1.13  Mar 18 2008
  - Included an "rsup" script for upgrading old RiveScript code.
  - Attempted to fix the package for CPAN (1.12 was a broken upload).
  - Bugfix: <bot> didn't have higher priority than <set>, so
    i.e. <set name=<bot name>> wouldn't work as expected. Fixed.

  1.12  Mar 16 2008
  - Initial beta release for a RiveScript 2.00 parser.