Created
January 27, 2010 09:35
-
-
Save sztupi/287694 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
namespace Gherkin.Lexer | |
{ | |
using System.Text; | |
using System.Text.RegularExpressions; | |
using System.IO; | |
using System.Collections.Generic; | |
public class En : ILexer { | |
%%{ | |
machine lexer; | |
alphtype char; | |
action begin_content { | |
contentStart = p; | |
currentLine = lineNumber; | |
} | |
action start_pystring { | |
currentLine = lineNumber; | |
startCol = p - lastNewline; | |
} | |
action begin_pystring_content { | |
contentStart = p; | |
} | |
action store_pystring_content { | |
string con = Unindent(startCol, new Regex("(\\r?\\n)?( )*\\Z").Replace(Substring(data, contentStart, nextKeywordStart-1), "", 1)); | |
listener.PythonString(con, currentLine); | |
} | |
action store_feature_content { | |
string con = MultilineStrip(KeywordContent(data, p, eof, nextKeywordStart, contentStart).Trim()); | |
listener.Feature(keyword, con, currentLine); | |
if(nextKeywordStart != -1) p = nextKeywordStart - 1; | |
nextKeywordStart = -1; | |
} | |
action store_background_content { | |
string con = MultilineStrip(KeywordContent(data, p, eof, nextKeywordStart, contentStart)); | |
listener.Background(keyword, con, currentLine); | |
if(nextKeywordStart != -1) p = nextKeywordStart - 1; | |
nextKeywordStart = -1; | |
} | |
action store_scenario_content { | |
string con = MultilineStrip(KeywordContent(data, p, eof, nextKeywordStart, contentStart)); | |
listener.Scenario(keyword, con, currentLine); | |
if(nextKeywordStart != -1) p = nextKeywordStart - 1; | |
nextKeywordStart = -1; | |
} | |
action store_scenario_outline_content { | |
string con = MultilineStrip(KeywordContent(data, p, eof, nextKeywordStart, contentStart)); | |
listener.ScenarioOutline(keyword, con, currentLine); | |
if(nextKeywordStart != -1) p = nextKeywordStart - 1; | |
nextKeywordStart = -1; | |
} | |
action store_examples_content { | |
string con = MultilineStrip(KeywordContent(data, p, eof, nextKeywordStart, contentStart)); | |
listener.Examples(keyword, con, currentLine); | |
if(nextKeywordStart != -1) p = nextKeywordStart - 1; | |
nextKeywordStart = -1; | |
} | |
action store_step_content { | |
listener.Step(keyword, Substring(data, contentStart, p).Trim(), currentLine); | |
} | |
action store_comment_content { | |
listener.Comment(Substring(data, contentStart, p).Trim(), lineNumber); | |
keywordStart = -1; | |
} | |
action store_tag_content { | |
listener.Tag(Substring(data, contentStart, p).Trim(), currentLine); | |
keywordStart = -1; | |
} | |
action inc_line_number { | |
lineNumber++; | |
} | |
action last_newline { | |
lastNewline = p + 1; | |
} | |
action start_keyword { | |
if(keywordStart == -1) keywordStart = p; | |
} | |
action end_keyword { | |
keyword = new Regex(":$").Replace(Substring(data, keywordStart, p), "", 1); | |
keywordStart = -1; | |
} | |
action next_keyword_start { | |
nextKeywordStart = p; | |
} | |
action start_table { | |
p = p - 1; | |
rows = new List<IList<string>>(); | |
currentLine = lineNumber; | |
} | |
action start_row { | |
currentRow = new List<string>(); | |
} | |
action begin_cell_content { | |
contentStart = p; | |
} | |
action store_cell_content { | |
currentRow.Add(Substring(data, contentStart, p).Trim()); | |
} | |
action store_row { | |
rows.Add(currentRow); | |
} | |
action store_table { | |
if(rows.Count > 0) { | |
listener.Table(rows, currentLine); | |
} | |
} | |
action end_feature { | |
if(cs < lexer_first_final) { | |
string content = CurrentLineContent(data, lastNewline); | |
throw new LexingException("Lexing error on line " + lineNumber); | |
} | |
} | |
include lexer_common "lexer_common.en.rl"; | |
}%% | |
private readonly IListener listener; | |
public En(IListener listener) { | |
this.listener = listener; | |
} | |
%% write data noerror; | |
public void Scan(TextReader inputSequence) { | |
string input = inputSequence.ReadToEnd() + "\n%_FEATURE_END_%"; | |
char[] data = input.ToCharArray(); | |
int cs, p = 0, pe = data.Length; | |
int eof = pe; | |
int lineNumber = 1; | |
int lastNewline = 0; | |
int contentStart = -1; | |
int currentLine = -1; | |
int startCol = -1; | |
int nextKeywordStart = -1; | |
int keywordStart = -1; | |
string keyword = null; | |
IList<IList<string>> rows = null; | |
IList<string> currentRow = null; | |
%% write init; | |
%% write exec; | |
} | |
private string KeywordContent(char[] data, int p, int eof, int nextKeywordStart, int contentStart) { | |
int endPoint = (nextKeywordStart == -1 || (p == eof)) ? p : nextKeywordStart; | |
return Substring(data, contentStart, endPoint); | |
} | |
private string MultilineStrip(string text) { | |
var result = new StringBuilder(); | |
foreach (var s in text.Split(new [] {'\n'})) { | |
result.AppendLine(s.Trim()); | |
} | |
return result.ToString().Trim(); | |
} | |
private string Unindent(int startCol, string text) { | |
return new Regex("^ {0," + startCol + "}", RegexOptions.Multiline).Replace(text, ""); | |
} | |
private string CurrentLineContent(char[] data, int lastNewline) { | |
return Substring(data, lastNewline, data.Length).Trim(); | |
} | |
private string Substring(char[] data, int start, int end) { | |
return new string(data, start, end-start); | |
} | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
%%{ | |
machine lexer_common; | |
# Language specific | |
I18N_Feature = (("Feature") ':') >start_keyword %end_keyword; | |
I18N_Background = (("Background") ':') >start_keyword %end_keyword; | |
I18N_ScenarioOutline = (("Scenario Outline") ':') >start_keyword %end_keyword; | |
I18N_Scenario = (("Scenario") ':') >start_keyword %end_keyword; | |
I18N_Step = ("* " | "Given " | "When " | "Then " | "And " | "But ") >start_keyword %end_keyword; | |
I18N_Examples = (("Examples" | "Scenarios") ':') >start_keyword %end_keyword; | |
EOF = '%_FEATURE_END_%'; # Explicit EOF added before scanning begins | |
EOL = ('\r'? '\n') @inc_line_number @last_newline; | |
FeatureHeadingEnd = EOL+ space* (I18N_Background | I18N_Scenario | I18N_ScenarioOutline | '@' | '#' | EOF) >next_keyword_start; | |
ScenarioHeadingEnd = EOL+ space* ( I18N_Scenario | I18N_ScenarioOutline | I18N_Step | '@' | '#' | EOF ) >next_keyword_start; | |
BackgroundHeadingEnd = EOL+ space* ( I18N_Scenario | I18N_ScenarioOutline | I18N_Step | '@' | '#'| EOF ) >next_keyword_start; | |
ScenarioOutlineHeadingEnd = EOL+ space* ( I18N_Scenario | I18N_Step | '@' | '#' | EOF ) >next_keyword_start; | |
ExamplesHeadingEnd = EOL+ space* '|' >next_keyword_start; | |
FeatureHeading = space* I18N_Feature %begin_content ^FeatureHeadingEnd* :>> FeatureHeadingEnd @store_feature_content; | |
BackgroundHeading = space* I18N_Background %begin_content ^BackgroundHeadingEnd* :>> BackgroundHeadingEnd @store_background_content; | |
ScenarioHeading = space* I18N_Scenario %begin_content ^ScenarioHeadingEnd* :>> ScenarioHeadingEnd @store_scenario_content; | |
ScenarioOutlineHeading = space* I18N_ScenarioOutline %begin_content ^ScenarioOutlineHeadingEnd* :>> ScenarioOutlineHeadingEnd @store_scenario_outline_content; | |
ExamplesHeading = space* I18N_Examples %begin_content ^ExamplesHeadingEnd* :>> ExamplesHeadingEnd @store_examples_content; | |
Step = space* I18N_Step %begin_content ^EOL+ %store_step_content EOL+; | |
Comment = space* '#' >begin_content ^EOL* %store_comment_content EOL+; | |
Tag = ( '@' [^@\r\n\t ]+ >begin_content ) %store_tag_content; | |
Tags = space* (Tag space*)+ EOL+; | |
StartTable = space* '|' >start_table; | |
EndTable = EOL space* ^('|') >next_keyword_start; | |
Cell = '|' (any - '|')* >begin_cell_content %store_cell_content; | |
Row = space* Cell* >start_row '|' :>> (space* EOL+ space*) %store_row; | |
Table = StartTable :>> Row+ %store_table <: EndTable?; | |
StartPyString = '"""' >start_pystring space* :>> EOL; | |
EndPyString = (space* '"""') >next_keyword_start; | |
PyString = space* StartPyString %begin_pystring_content (^EOL | EOL)* :>> EndPyString %store_pystring_content space* EOL+; | |
Tokens = (space | EOL)* (Tags | Comment | FeatureHeading | BackgroundHeading | ScenarioHeading | ScenarioOutlineHeading | ExamplesHeading | Step | Table | PyString)* (space | EOL)* EOF; | |
main := Tokens %end_feature @!end_feature; | |
}%% |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment