X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Flexer%2Flexer.h;h=b9e936bf994c67cdb7d6952950196f57170b3cf3;hb=9ade26c8349b4434008c46cf09bc7473ec743972;hp=4f9259250dadbd3fe5985afeef259ff584b64df6;hpb=480a0746507ce73d26f528b56dc3ed80195096e0;p=pspp-builds.git diff --git a/src/language/lexer/lexer.h b/src/language/lexer/lexer.h index 4f925925..b9e936bf 100644 --- a/src/language/lexer/lexer.h +++ b/src/language/lexer/lexer.h @@ -1,97 +1,174 @@ -/* PSPP - computes sample statistics. - Copyright (C) 1997-9, 2000 Free Software Foundation, Inc. +/* PSPP - a program for statistical analysis. + Copyright (C) 1997-9, 2000, 2010, 2011 Free Software Foundation, Inc. - This program is free software; you can redistribute it and/or - modify it under the terms of the GNU General Public License as - published by the Free Software Foundation; either version 2 of the - License, or (at your option) any later version. + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with this program. If not, see . */ -#if !lexer_h -#define lexer_h 1 +#ifndef LEXER_H +#define LEXER_H 1 -#include #include #include -#include -#include -#include + +#include "data/identifier.h" +#include "data/variable.h" +#include "libpspp/compiler.h" +#include "libpspp/prompt.h" struct lexer; +/* The syntax mode for which a syntax file is intended. */ +enum lex_syntax_mode + { + LEX_SYNTAX_AUTO, /* Try to guess intent. */ + LEX_SYNTAX_INTERACTIVE, /* Interactive mode. */ + LEX_SYNTAX_BATCH /* Batch mode. */ + }; + +/* Handling of errors. */ +enum lex_error_mode + { + LEX_ERROR_INTERACTIVE, /* Always continue to next command. */ + LEX_ERROR_CONTINUE, /* Continue to next command, except for + cascading failures. */ + LEX_ERROR_STOP /* Stop processing. */ + }; + +/* Reads a single syntax file as a stream of bytes encoded in UTF-8. + + Not opaque. */ +struct lex_reader + { + const struct lex_reader_class *class; + enum lex_syntax_mode syntax; + enum lex_error_mode error; + char *file_name; /* NULL if not associated with a file. */ + int line_number; /* 1-based initial line number, 0 if none. */ + }; + +/* An implementation of a lex_reader. */ +struct lex_reader_class + { + /* Reads up to N bytes of data from READER into N. Returns the positive + number of bytes read if successful, or zero at end of input or on + error. + + STYLE provides a hint to interactive readers as to what kind of syntax + is being read right now. */ + size_t (*read) (struct lex_reader *reader, char *buf, size_t n, + enum prompt_style style); + + /* Closes and destroys READER, releasing any allocated storage. + + The caller will free the 'file_name' member of READER, so the + implementation should not do so. */ + void (*close) (struct lex_reader *reader); + }; + +/* Helper functions for lex_reader. */ +void lex_reader_init (struct lex_reader *, const struct lex_reader_class *); +void lex_reader_set_file_name (struct lex_reader *, const char *file_name); + +/* Creating various kinds of lex_readers. */ +struct lex_reader *lex_reader_for_file (const char *file_name, + const char *encoding, + enum lex_syntax_mode syntax, + enum lex_error_mode error); +struct lex_reader *lex_reader_for_string (const char *); +struct lex_reader *lex_reader_for_format (const char *, ...) + PRINTF_FORMAT (1, 2); +struct lex_reader *lex_reader_for_substring_nocopy (struct substring); + /* Initialization. */ -struct lexer * lex_create (struct source_stream *); +struct lexer *lex_create (void); void lex_destroy (struct lexer *); -struct source_stream * lex_get_source_stream (const struct lexer *); +/* Files. */ +void lex_include (struct lexer *, struct lex_reader *); +void lex_append (struct lexer *, struct lex_reader *); - -/* Common functions. */ +/* Advancing. */ void lex_get (struct lexer *); -void lex_error (struct lexer *, const char *, ...); -void lex_sbc_only_once (const char *); -void lex_sbc_missing (struct lexer *, const char *); -int lex_end_of_command (struct lexer *); /* Token testing functions. */ bool lex_is_number (struct lexer *); double lex_number (struct lexer *); bool lex_is_integer (struct lexer *); long lex_integer (struct lexer *); +bool lex_is_string (struct lexer *); + +/* Token testing functions with lookahead. */ +bool lex_next_is_number (struct lexer *, int n); +double lex_next_number (struct lexer *, int n); +bool lex_next_is_integer (struct lexer *, int n); +long lex_next_integer (struct lexer *, int n); +bool lex_next_is_string (struct lexer *, int n); /* Token matching functions. */ -bool lex_match (struct lexer *, int); +bool lex_match (struct lexer *, enum token_type); bool lex_match_id (struct lexer *, const char *); +bool lex_match_id_n (struct lexer *, const char *, size_t n); bool lex_match_int (struct lexer *, int); +bool lex_match_phrase (struct lexer *, const char *s); /* Forcible matching functions. */ -bool lex_force_match (struct lexer *, int); +bool lex_force_match (struct lexer *, enum token_type); bool lex_force_match_id (struct lexer *, const char *); bool lex_force_int (struct lexer *); bool lex_force_num (struct lexer *); bool lex_force_id (struct lexer *); bool lex_force_string (struct lexer *); - -/* Weird token functions. */ -int lex_look_ahead (struct lexer *); -void lex_put_back (struct lexer *, int); -void lex_put_back_id (struct lexer *, const char *tokid); - -/* Weird line processing functions. */ -const char *lex_entire_line (struct lexer *); -const struct string *lex_entire_line_ds (struct lexer *); -const char *lex_rest_of_line (struct lexer *, int *end_dot); -void lex_preprocess_line (struct string *, enum getl_syntax, - bool *line_starts_command, - bool *line_ends_command); -void lex_discard_line (struct lexer *); -void lex_discard_rest_of_command (struct lexer *); -/* Weird line reading functions. */ -bool lex_get_line (struct lexer *); -bool lex_get_line_raw (struct lexer *, enum getl_syntax *); +/* Token accessors. */ +enum token_type lex_token (const struct lexer *); +double lex_tokval (const struct lexer *); +const char *lex_tokcstr (const struct lexer *); +struct substring lex_tokss (const struct lexer *); + +/* Looking ahead. */ +const struct token *lex_next (const struct lexer *, int n); +enum token_type lex_next_token (const struct lexer *, int n); +const char *lex_next_tokcstr (const struct lexer *, int n); +double lex_next_tokval (const struct lexer *, int n); +struct substring lex_next_tokss (const struct lexer *, int n); + +/* Current position. */ +int lex_get_first_line_number (const struct lexer *, int n); +int lex_get_last_line_number (const struct lexer *, int n); +int lex_get_first_column (const struct lexer *, int n); +int lex_get_last_column (const struct lexer *, int n); +const char *lex_get_file_name (const struct lexer *); + +/* Issuing errors. */ +void lex_error (struct lexer *, const char *, ...) PRINTF_FORMAT (2, 3); +void lex_next_error (struct lexer *, int n0, int n1, const char *, ...) + PRINTF_FORMAT (4, 5); +int lex_end_of_command (struct lexer *); -/* Token names. */ -const char *lex_token_name (int); -char *lex_token_representation (struct lexer *); +void lex_sbc_only_once (const char *); +void lex_sbc_missing (struct lexer *, const char *); -/* Token accessors */ -int lex_token (const struct lexer *); -double lex_tokval (const struct lexer *); -const char *lex_tokid (const struct lexer *); -const struct string *lex_tokstr (const struct lexer *); +void lex_error_valist (struct lexer *, const char *, va_list) + PRINTF_FORMAT (2, 0); +void lex_next_error_valist (struct lexer *lexer, int n0, int n1, + const char *format, va_list) + PRINTF_FORMAT (4, 0); -/* Really weird functions. */ -void lex_negative_to_dash (struct lexer *); -void lex_skip_comment (struct lexer *); +/* Error handling. */ +enum lex_syntax_mode lex_get_syntax_mode (const struct lexer *); +enum lex_error_mode lex_get_error_mode (const struct lexer *); +void lex_discard_rest_of_command (struct lexer *); +void lex_interactive_reset (struct lexer *); +void lex_discard_noninteractive (struct lexer *); -#endif /* !lexer_h */ +#endif /* lexer.h */