tartrazine/_testdata/Java/JFlexLexer.java
Miguel Molina 8ff885a3a8
implement IsGenerated helper to filter out generated files
Closes #17

Implements the IsGenerated helper function to filter out generated
files using the rules and matchers in:
- https://github.com/github/linguist/blob/master/lib/linguist/generated.rb

Since the vast majority of matchers have very different logic, it cannot
be autogenerated directly from linguist like other logics in enry, so it's
translated by hand.

There are three different types of matchers in this implementation:
- By extension, which mark as generated based only in the extension. These
  are the fastest matchers, so they're done first.
- By file name, which matches patterns against the filename. These
  are performed in second place. Unlike linguist, we try to use string
  functions instead of regexps as much as possible.
- Finally, the rest of the matchers, which go into the content and try
  to identify if they're generated or not based on the content. Unlike
  linguist, we try to only read the content we need and not split it
  all unless it's necessary and use byte functions instead of regexps
  as much as possible.

Signed-off-by: Miguel Molina <miguel@erizocosmi.co>
2020-05-28 08:55:13 +02:00

483 lines
13 KiB
Java

/* The following code was generated by JFlex 1.4.3 on 28/01/16 11:27 */
package test;
import com.intellij.lexer.*;
import com.intellij.psi.tree.IElementType;
import static org.intellij.grammar.psi.BnfTypes.*;
/**
* This class is a scanner generated by
* <a href="http://www.jflex.de/">JFlex</a> 1.4.3
* on 28/01/16 11:27 from the specification file
* <tt>/home/abigail/code/intellij-grammar-kit-test/src/test/_GrammarLexer.flex</tt>
*/
public class _GrammarLexer implements FlexLexer {
/** initial size of the lookahead buffer */
private static final int ZZ_BUFFERSIZE = 16384;
/** lexical states */
public static final int YYINITIAL = 0;
/**
* ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l
* ZZ_LEXSTATE[l+1] is the state in the DFA for the lexical state l
* at the beginning of a line
* l is of the form l = 2*k, k a non negative integer
*/
private static final int ZZ_LEXSTATE[] = {
0, 0
};
/**
* Translates characters to character classes
*/
private static final String ZZ_CMAP_PACKED =
"\11\0\1\1\1\1\1\0\1\1\1\1\22\0\1\1\101\0\1\13"+
"\1\0\1\3\1\14\1\0\1\10\1\0\1\2\3\0\1\12\1\7"+
"\3\0\1\6\1\4\1\5\1\11\uff8a\0";
/**
* Translates characters to character classes
*/
private static final char [] ZZ_CMAP = zzUnpackCMap(ZZ_CMAP_PACKED);
/**
* Translates DFA states to action switch labels.
*/
private static final int [] ZZ_ACTION = zzUnpackAction();
private static final String ZZ_ACTION_PACKED_0 =
"\1\0\1\1\1\2\3\1\1\3\10\0\1\4\1\5";
private static int [] zzUnpackAction() {
int [] result = new int[17];
int offset = 0;
offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result);
return result;
}
private static int zzUnpackAction(String packed, int offset, int [] result) {
int i = 0; /* index in packed string */
int j = offset; /* index in unpacked array */
int l = packed.length();
while (i < l) {
int count = packed.charAt(i++);
int value = packed.charAt(i++);
do result[j++] = value; while (--count > 0);
}
return j;
}
/**
* Translates a state to a row index in the transition table
*/
private static final int [] ZZ_ROWMAP = zzUnpackRowMap();
private static final String ZZ_ROWMAP_PACKED_0 =
"\0\0\0\15\0\32\0\47\0\64\0\101\0\15\0\116"+
"\0\133\0\150\0\165\0\202\0\217\0\234\0\251\0\15"+
"\0\15";
private static int [] zzUnpackRowMap() {
int [] result = new int[17];
int offset = 0;
offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result);
return result;
}
private static int zzUnpackRowMap(String packed, int offset, int [] result) {
int i = 0; /* index in packed string */
int j = offset; /* index in unpacked array */
int l = packed.length();
while (i < l) {
int high = packed.charAt(i++) << 16;
result[j++] = high | packed.charAt(i++);
}
return j;
}
/**
* The transition table of the DFA
*/
private static final int [] ZZ_TRANS = zzUnpackTrans();
private static final String ZZ_TRANS_PACKED_0 =
"\1\2\1\3\1\4\1\2\1\5\2\2\1\6\5\2"+
"\16\0\1\3\16\0\1\7\16\0\1\10\20\0\1\11"+
"\11\0\1\12\20\0\1\13\4\0\1\14\25\0\1\15"+
"\10\0\1\16\21\0\1\17\10\0\1\20\12\0\1\21"+
"\6\0";
private static int [] zzUnpackTrans() {
int [] result = new int[182];
int offset = 0;
offset = zzUnpackTrans(ZZ_TRANS_PACKED_0, offset, result);
return result;
}
private static int zzUnpackTrans(String packed, int offset, int [] result) {
int i = 0; /* index in packed string */
int j = offset; /* index in unpacked array */
int l = packed.length();
while (i < l) {
int count = packed.charAt(i++);
int value = packed.charAt(i++);
value--;
do result[j++] = value; while (--count > 0);
}
return j;
}
/* error codes */
private static final int ZZ_UNKNOWN_ERROR = 0;
private static final int ZZ_NO_MATCH = 1;
private static final int ZZ_PUSHBACK_2BIG = 2;
private static final char[] EMPTY_BUFFER = new char[0];
private static final int YYEOF = -1;
private static java.io.Reader zzReader = null; // Fake
/* error messages for the codes above */
private static final String ZZ_ERROR_MSG[] = {
"Unkown internal scanner error",
"Error: could not match input",
"Error: pushback value was too large"
};
/**
* ZZ_ATTRIBUTE[aState] contains the attributes of state <code>aState</code>
*/
private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
private static final String ZZ_ATTRIBUTE_PACKED_0 =
"\1\0\1\11\4\1\1\11\10\0\2\11";
private static int [] zzUnpackAttribute() {
int [] result = new int[17];
int offset = 0;
offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result);
return result;
}
private static int zzUnpackAttribute(String packed, int offset, int [] result) {
int i = 0; /* index in packed string */
int j = offset; /* index in unpacked array */
int l = packed.length();
while (i < l) {
int count = packed.charAt(i++);
int value = packed.charAt(i++);
do result[j++] = value; while (--count > 0);
}
return j;
}
/** the current state of the DFA */
private int zzState;
/** the current lexical state */
private int zzLexicalState = YYINITIAL;
/** this buffer contains the current text to be matched and is
the source of the yytext() string */
private CharSequence zzBuffer = "";
/** this buffer may contains the current text array to be matched when it is cheap to acquire it */
private char[] zzBufferArray;
/** the textposition at the last accepting state */
private int zzMarkedPos;
/** the textposition at the last state to be included in yytext */
private int zzPushbackPos;
/** the current text position in the buffer */
private int zzCurrentPos;
/** startRead marks the beginning of the yytext() string in the buffer */
private int zzStartRead;
/** endRead marks the last character in the buffer, that has been read
from input */
private int zzEndRead;
/**
* zzAtBOL == true <=> the scanner is currently at the beginning of a line
*/
private boolean zzAtBOL = true;
/** zzAtEOF == true <=> the scanner is at the EOF */
private boolean zzAtEOF;
/* user code: */
public _GrammarLexer() {
this((java.io.Reader)null);
}
/**
* Creates a new scanner
*
* @param in the java.io.Reader to read input from.
*/
public _GrammarLexer(java.io.Reader in) {
this.zzReader = in;
}
/**
* Unpacks the compressed character translation table.
*
* @param packed the packed character translation table
* @return the unpacked character translation table
*/
private static char [] zzUnpackCMap(String packed) {
char [] map = new char[0x10000];
int i = 0; /* index in packed string */
int j = 0; /* index in unpacked array */
while (i < 52) {
int count = packed.charAt(i++);
char value = packed.charAt(i++);
do map[j++] = value; while (--count > 0);
}
return map;
}
public final int getTokenStart(){
return zzStartRead;
}
public final int getTokenEnd(){
return getTokenStart() + yylength();
}
public void reset(CharSequence buffer, int start, int end,int initialState){
zzBuffer = buffer;
zzBufferArray = com.intellij.util.text.CharArrayUtil.fromSequenceWithoutCopying(buffer);
zzCurrentPos = zzMarkedPos = zzStartRead = start;
zzPushbackPos = 0;
zzAtEOF = false;
zzAtBOL = true;
zzEndRead = end;
yybegin(initialState);
}
/**
* Refills the input buffer.
*
* @return <code>false</code>, iff there was new input.
*
* @exception java.io.IOException if any I/O-Error occurs
*/
private boolean zzRefill() throws java.io.IOException {
return true;
}
/**
* Returns the current lexical state.
*/
public final int yystate() {
return zzLexicalState;
}
/**
* Enters a new lexical state
*
* @param newState the new lexical state
*/
public final void yybegin(int newState) {
zzLexicalState = newState;
}
/**
* Returns the text matched by the current regular expression.
*/
public final CharSequence yytext() {
return zzBuffer.subSequence(zzStartRead, zzMarkedPos);
}
/**
* Returns the character at position <tt>pos</tt> from the
* matched text.
*
* It is equivalent to yytext().charAt(pos), but faster
*
* @param pos the position of the character to fetch.
* A value from 0 to yylength()-1.
*
* @return the character at position pos
*/
public final char yycharat(int pos) {
return zzBufferArray != null ? zzBufferArray[zzStartRead+pos]:zzBuffer.charAt(zzStartRead+pos);
}
/**
* Returns the length of the matched text region.
*/
public final int yylength() {
return zzMarkedPos-zzStartRead;
}
/**
* Reports an error that occured while scanning.
*
* In a wellformed scanner (no or only correct usage of
* yypushback(int) and a match-all fallback rule) this method
* will only be called with things that "Can't Possibly Happen".
* If this method is called, something is seriously wrong
* (e.g. a JFlex bug producing a faulty scanner etc.).
*
* Usual syntax/scanner level error handling should be done
* in error fallback rules.
*
* @param errorCode the code of the errormessage to display
*/
private void zzScanError(int errorCode) {
String message;
try {
message = ZZ_ERROR_MSG[errorCode];
}
catch (ArrayIndexOutOfBoundsException e) {
message = ZZ_ERROR_MSG[ZZ_UNKNOWN_ERROR];
}
throw new Error(message);
}
/**
* Pushes the specified amount of characters back into the input stream.
*
* They will be read again by then next call of the scanning method
*
* @param number the number of characters to be read again.
* This number must not be greater than yylength()!
*/
public void yypushback(int number) {
if ( number > yylength() )
zzScanError(ZZ_PUSHBACK_2BIG);
zzMarkedPos -= number;
}
/**
* Resumes scanning until the next regular expression is matched,
* the end of input is encountered or an I/O-Error occurs.
*
* @return the next token
* @exception java.io.IOException if any I/O-Error occurs
*/
public IElementType advance() throws java.io.IOException {
int zzInput;
int zzAction;
// cached fields:
int zzCurrentPosL;
int zzMarkedPosL;
int zzEndReadL = zzEndRead;
CharSequence zzBufferL = zzBuffer;
char[] zzBufferArrayL = zzBufferArray;
char [] zzCMapL = ZZ_CMAP;
int [] zzTransL = ZZ_TRANS;
int [] zzRowMapL = ZZ_ROWMAP;
int [] zzAttrL = ZZ_ATTRIBUTE;
while (true) {
zzMarkedPosL = zzMarkedPos;
zzAction = -1;
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
zzState = ZZ_LEXSTATE[zzLexicalState];
zzForAction: {
while (true) {
if (zzCurrentPosL < zzEndReadL)
zzInput = (zzBufferArrayL != null ? zzBufferArrayL[zzCurrentPosL++] : zzBufferL.charAt(zzCurrentPosL++));
else if (zzAtEOF) {
zzInput = YYEOF;
break zzForAction;
}
else {
// store back cached positions
zzCurrentPos = zzCurrentPosL;
zzMarkedPos = zzMarkedPosL;
boolean eof = zzRefill();
// get translated positions and possibly new buffer
zzCurrentPosL = zzCurrentPos;
zzMarkedPosL = zzMarkedPos;
zzBufferL = zzBuffer;
zzEndReadL = zzEndRead;
if (eof) {
zzInput = YYEOF;
break zzForAction;
}
else {
zzInput = (zzBufferArrayL != null ? zzBufferArrayL[zzCurrentPosL++] : zzBufferL.charAt(zzCurrentPosL++));
}
}
int zzNext = zzTransL[ zzRowMapL[zzState] + zzCMapL[zzInput] ];
if (zzNext == -1) break zzForAction;
zzState = zzNext;
int zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
zzMarkedPosL = zzCurrentPosL;
if ( (zzAttributes & 8) == 8 ) break zzForAction;
}
}
}
// store back cached position
zzMarkedPos = zzMarkedPosL;
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
case 1:
{ return com.intellij.psi.TokenType.BAD_CHARACTER;
}
case 6: break;
case 4:
{ return BNF_STRING;
}
case 7: break;
case 5:
{ return BNF_NUMBER;
}
case 8: break;
case 3:
{ return BNF_ID;
}
case 9: break;
case 2:
{ return com.intellij.psi.TokenType.WHITE_SPACE;
}
case 10: break;
default:
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
return null;
}
else {
zzScanError(ZZ_NO_MATCH);
}
}
}
}
}