[python] extract python parser to a separate module

Merge-request: IJ-MR-116296
Merged-by: Vladimir Koshelev <Vladimir.Koshelev@jetbrains.com>

GitOrigin-RevId: e7559fb3215d757e6273543e4aa27d52df755e63
This commit is contained in:
Vladimir Koshelev
2023-10-09 11:56:10 +00:00
committed by intellij-monorepo-bot
parent 609391377b
commit 29f0eb6c77
76 changed files with 3494 additions and 572 deletions

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,565 @@
// Generated by JFlex 1.9.1 http://jflex.de/ (tweaked for IntelliJ platform)
// source: PyType.flex
package com.jetbrains.python.psi.types;
import com.intellij.lexer.FlexLexer;
import com.jetbrains.python.psi.PyElementType;
import static com.jetbrains.python.psi.types.PyTypeTokenTypes.*;
public class _PyTypeLexer implements FlexLexer {
/** This character denotes the end of file */
public static final int YYEOF = -1;
/** 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
};
/**
* Top-level table for translating characters to character classes
*/
private static final int [] ZZ_CMAP_TOP = zzUnpackcmap_top();
private static final String ZZ_CMAP_TOP_PACKED_0 =
"\1\0\u10ff\u0100";
private static int [] zzUnpackcmap_top() {
int [] result = new int[4352];
int offset = 0;
offset = zzUnpackcmap_top(ZZ_CMAP_TOP_PACKED_0, offset, result);
return result;
}
private static int zzUnpackcmap_top(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;
}
/**
* Second-level tables for translating characters to character classes
*/
private static final int [] ZZ_CMAP_BLOCKS = zzUnpackcmap_blocks();
private static final String ZZ_CMAP_BLOCKS_PACKED_0 =
"\11\0\1\1\1\2\2\0\1\2\22\0\1\1\1\3"+
"\6\0\3\4\1\0\1\4\1\5\1\6\1\0\12\7"+
"\1\10\1\0\1\11\1\12\1\13\2\0\23\14\7\15"+
"\1\4\1\0\1\4\1\0\1\16\1\17\1\20\1\16"+
"\1\21\2\16\1\22\5\16\1\23\1\24\1\16\1\25"+
"\1\26\1\16\1\27\1\30\1\31\4\16\1\32\1\16"+
"\1\33\1\4\1\34\1\3\u0181\0";
private static int [] zzUnpackcmap_blocks() {
int [] result = new int[512];
int offset = 0;
offset = zzUnpackcmap_blocks(ZZ_CMAP_BLOCKS_PACKED_0, offset, result);
return result;
}
private static int zzUnpackcmap_blocks(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 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\1\3\1\0\1\3\2\0\1\4"+
"\1\5\1\4\1\6\3\4\3\0\1\4\1\3\2\0"+
"\1\4\5\0\1\6";
private static int [] zzUnpackAction() {
int [] result = new int[29];
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\35\0\72\0\35\0\127\0\164\0\221\0\256"+
"\0\313\0\313\0\350\0\35\0\u0105\0\u0122\0\u013f\0\u015c"+
"\0\u0179\0\u0196\0\u01b3\0\350\0\u01d0\0\u01ed\0\u020a\0\u0227"+
"\0\u0244\0\u0261\0\u027e\0\u029b\0\u02b8";
private static int [] zzUnpackRowMap() {
int [] result = new int[29];
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() - 1;
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\0\1\2\1\3\1\0\1\4\1\5\1\6\1\0"+
"\1\7\1\10\2\0\1\11\1\12\1\13\1\14\2\13"+
"\1\15\2\13\1\16\3\13\1\17\1\13\1\0\1\14"+
"\37\0\1\3\45\0\1\4\27\0\1\20\47\0\1\21"+
"\4\0\1\22\20\0\1\4\31\0\1\13\4\0\3\13"+
"\1\0\13\13\1\14\10\0\1\13\4\0\3\13\1\0"+
"\13\13\11\0\1\13\4\0\3\13\1\0\7\13\1\23"+
"\3\13\11\0\1\13\4\0\3\13\1\0\2\13\1\24"+
"\4\13\1\24\3\13\11\0\1\13\4\0\3\13\1\0"+
"\5\13\1\24\5\13\10\0\1\4\51\0\1\25\43\0"+
"\1\26\11\0\1\13\4\0\3\13\1\0\5\13\1\27"+
"\5\13\22\0\1\30\24\0\1\31\33\0\1\13\4\0"+
"\3\13\1\0\4\13\1\24\6\13\32\0\1\32\25\0"+
"\1\21\43\0\1\33\14\0\1\34\43\0\1\35\20\0"+
"\1\14\31\0";
private static int [] zzUnpacktrans() {
int [] result = new int[725];
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;
/* error messages for the codes above */
private static final String[] ZZ_ERROR_MSG = {
"Unknown internal scanner error",
"Error: could not match input",
"Error: pushback value was too large"
};
/**
* ZZ_ATTRIBUTE[aState] contains the attributes of state {@code aState}
*/
private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
private static final String ZZ_ATTRIBUTE_PACKED_0 =
"\1\0\1\11\1\1\1\11\1\0\1\1\2\0\3\1"+
"\1\11\3\1\3\0\2\1\2\0\1\1\5\0\1\1";
private static int [] zzUnpackAttribute() {
int [] result = new int[29];
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 input device */
private java.io.Reader zzReader;
/** 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 = "";
/** the textposition at the last accepting state */
private int zzMarkedPos;
/** 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;
/** zzAtEOF == true <=> the scanner is at the EOF */
private boolean zzAtEOF;
/** Number of newlines encountered up to the start of the matched text. */
@SuppressWarnings("unused")
private int yyline;
/** Number of characters from the last newline up to the start of the matched text. */
@SuppressWarnings("unused")
protected int yycolumn;
/** Number of characters up to the start of the matched text. */
@SuppressWarnings("unused")
private long yychar;
/** Whether the scanner is currently at the beginning of a line. */
@SuppressWarnings("unused")
private boolean zzAtBOL = true;
/** Whether the user-EOF-code has already been executed. */
@SuppressWarnings("unused")
private boolean zzEOFDone;
/**
* Creates a new scanner
*
* @param in the java.io.Reader to read input from.
*/
public _PyTypeLexer(java.io.Reader in) {
this.zzReader = in;
}
/** Returns the maximum size of the scanner buffer, which limits the size of tokens. */
private int zzMaxBufferLen() {
return Integer.MAX_VALUE;
}
/** Whether the scanner buffer can grow to accommodate a larger token. */
private boolean zzCanGrow() {
return true;
}
/**
* Translates raw input code points to DFA table row
*/
private static int zzCMap(int input) {
int offset = input & 255;
return offset == input ? ZZ_CMAP_BLOCKS[offset] : ZZ_CMAP_BLOCKS[ZZ_CMAP_TOP[input >> 8] | offset];
}
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;
zzCurrentPos = zzMarkedPos = zzStartRead = start;
zzAtEOF = false;
zzAtBOL = true;
zzEndRead = end;
yybegin(initialState);
}
/**
* Refills the input buffer.
*
* @return {@code false}, 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 {@code pos} 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 zzBuffer.charAt(zzStartRead+pos);
}
/**
* Returns the length of the matched text region.
*/
public final int yylength() {
return zzMarkedPos-zzStartRead;
}
/**
* Reports an error that occurred 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 PyElementType advance() throws java.io.IOException
{
int zzInput;
int zzAction;
// cached fields:
int zzCurrentPosL;
int zzMarkedPosL;
int zzEndReadL = zzEndRead;
CharSequence zzBufferL = zzBuffer;
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];
// set up zzAction for empty match case:
int zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
}
zzForAction: {
while (true) {
if (zzCurrentPosL < zzEndReadL) {
zzInput = Character.codePointAt(zzBufferL, zzCurrentPosL);
zzCurrentPosL += Character.charCount(zzInput);
}
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 = Character.codePointAt(zzBufferL, zzCurrentPosL);
zzCurrentPosL += Character.charCount(zzInput);
}
}
int zzNext = zzTransL[ zzRowMapL[zzState] + zzCMap(zzInput) ];
if (zzNext == -1) break zzForAction;
zzState = zzNext;
zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
zzMarkedPosL = zzCurrentPosL;
if ( (zzAttributes & 8) == 8 ) break zzForAction;
}
}
}
// store back cached position
zzMarkedPos = zzMarkedPosL;
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
return null;
}
else {
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
case 1:
{ return SPACE;
}
// fall through
case 7: break;
case 2:
{ return NL;
}
// fall through
case 8: break;
case 3:
{ return OP;
}
// fall through
case 9: break;
case 4:
{ return IDENTIFIER;
}
// fall through
case 10: break;
case 5:
{ return PARAMETER;
}
// fall through
case 11: break;
case 6:
{ return MARKUP;
}
// fall through
case 12: break;
default:
zzScanError(ZZ_NO_MATCH);
}
}
}
}
}