From deae06da9f6a9b99b20d33d0111c8f358e38f1a8 Mon Sep 17 00:00:00 2001 From: Jan Breuer <jan.breuer@jaybee.cz> Date: 周一, 10 8月 2015 20:08:37 +0800 Subject: [PATCH] Resolve #39: Correct handling of unsigned integers --- libscpi/src/lexer.c | 304 +++++++++++++++++++++++++++++++++++++++++--------- 1 files changed, 249 insertions(+), 55 deletions(-) diff --git a/libscpi/src/lexer.c b/libscpi/src/lexer.c index 9060d2f..45b19ce 100644 --- a/libscpi/src/lexer.c +++ b/libscpi/src/lexer.c @@ -39,8 +39,13 @@ #include <string.h> #include "lexer_private.h" +#include "scpi/error.h" -/* identify character */ +/** + * Is white space + * @param c + * @return + */ static int isws(int c) { if ((c == ' ') || (c == '\t')) { return 1; @@ -48,6 +53,11 @@ return 0; } +/** + * Is binary digit + * @param c + * @return + */ static int isbdigit(int c) { if ((c == '0') || (c == '1')) { return 1; @@ -55,6 +65,11 @@ return 0; } +/** + * Is hexadecimal digit + * @param c + * @return + */ static int isqdigit(int c) { if ((c == '0') || (c == '1') || (c == '2') || (c == '3') || (c == '4') || (c == '5') || (c == '6') || (c == '7')) { return 1; @@ -62,6 +77,11 @@ return 0; } +/** + * Is end of string + * @param state + * @return + */ static int iseos(lex_state_t * state) { if ((state->buffer + state->len) <= (state->pos)) { return 1; @@ -70,30 +90,66 @@ } } +/** + * Private export of iseos + * @param state + * @return + */ int scpiLex_IsEos(lex_state_t * state) { return iseos(state); } +/** + * Test current character + * @param state + * @param chr + * @return + */ static int ischr(lex_state_t * state, char chr) { return (state->pos[0] == chr); } +/** + * Is plus or minus + * @param c + * @return + */ static int isplusmn(int c) { return c == '+' || c == '-'; } +/** + * Is letter H + * @param c + * @return + */ static int isH(int c) { return c == 'h' || c == 'H'; } +/** + * Is letter B + * @param c + * @return + */ static int isB(int c) { return c == 'b' || c == 'B'; } +/** + * Is letter Q + * @param c + * @return + */ static int isQ(int c) { return c == 'q' || c == 'Q'; } +/** + * Is letter E + * @param c + * @return + */ static int isE(int c) { return c == 'e' || c == 'E'; } @@ -106,6 +162,11 @@ /* 7.4.1 <PROGRAM MESSAGE UNIT SEPARATOR>*/ // TODO: static int skipProgramMessageUnitSeparator(lex_state_t * state) +/** + * Skip all whitespaces + * @param state + * @return + */ static int skipWs(lex_state_t * state) { int someSpace = 0; while (!iseos(state) && isws(state->pos[0])) { @@ -122,6 +183,11 @@ /* 7.5.2 <PROGRAM MESSAGE TERMINATOR> */ // static int skipProgramMessageTerminator(lex_state_t * state) +/** + * Skip decimal digit + * @param state + * @return + */ static int skipDigit(lex_state_t * state) { if (!iseos(state) && isdigit(state->pos[0])) { state->pos++; @@ -131,6 +197,11 @@ } } +/** + * Skip multiple decimal digits + * @param state + * @return + */ static int skipNumbers(lex_state_t * state) { int someNumbers = 0; while (!iseos(state) && isdigit(state->pos[0])) { @@ -140,6 +211,11 @@ return someNumbers; } +/** + * Skip plus or minus + * @param state + * @return + */ static int skipPlusmn(lex_state_t * state) { if (!iseos(state) && isplusmn(state->pos[0])) { state->pos++; @@ -149,6 +225,11 @@ } } +/** + * Skip any character from 'a'-'Z' + * @param state + * @return + */ static int skipAlpha(lex_state_t * state) { int someLetters = 0; while (!iseos(state) && isalpha(state->pos[0])) { @@ -158,7 +239,13 @@ return someLetters; } -static int skipChr(lex_state_t * state, int chr) { +/** + * Skip exact character chr or nothing + * @param state + * @param chr + * @return + */ +static int skipChr(lex_state_t * state, char chr) { if (!iseos(state) && ischr(state, chr)) { state->pos++; return SKIP_OK; @@ -167,6 +254,11 @@ } } +/** + * Skip slash or dot + * @param state + * @return + */ static int skipSlashDot(lex_state_t * state) { if (!iseos(state) && (ischr(state, '/') | ischr(state, '.'))) { state->pos++; @@ -176,6 +268,11 @@ } } +/** + * Skip star + * @param state + * @return + */ static int skipStar(lex_state_t * state) { if (!iseos(state) && ischr(state, '*')) { state->pos++; @@ -185,6 +282,11 @@ } } +/** + * Skip colon + * @param state + * @return + */ static int skipColon(lex_state_t * state) { if (!iseos(state) && ischr(state, ':')) { state->pos++; @@ -195,6 +297,12 @@ } /* 7.6.1.2 <COMMAND PROGRAM HEADER> */ + +/** + * Skip program mnemonic [a-z][a-z0-9_]* + * @param state + * @return + */ static int skipProgramMnemonic(lex_state_t * state) { const char * startPos = state->pos; if (!iseos(state) && isalpha(state->pos[0])) { @@ -212,6 +320,13 @@ } /* tokens */ + +/** + * Detect token white space + * @param state + * @param token + * @return + */ int scpiLex_WhiteSpace(lex_state_t * state, scpi_token_t * token) { token->ptr = state->pos; @@ -220,15 +335,21 @@ token->len = state->pos - token->ptr; if (token->len > 0) { - token->type = TokWhiteSpace; + token->type = SCPI_TOKEN_WS; } else { - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; } return token->len; } /* 7.6.1 <COMMAND PROGRAM HEADER> */ + +/** + * Skip command program header \*<PROGRAM MNEMONIC> + * @param state + * @return + */ static int skipCommonProgramHeader(lex_state_t * state) { int res; if (skipStar(state)) { @@ -246,6 +367,11 @@ return SKIP_NONE; } +/** + * Skip compound program header :<PROGRAM MNEMONIC>:<PROGRAM MNEMONIC>... + * @param state + * @return + */ static int skipCompoundProgramHeader(lex_state_t * state) { int res; int firstColon = skipColon(state); @@ -270,35 +396,41 @@ } } +/** + * Detect token command or compound program header + * @param state + * @param token + * @return + */ int scpiLex_ProgramHeader(lex_state_t * state, scpi_token_t * token) { int res; token->ptr = state->pos; - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; res = skipCommonProgramHeader(state); if (res >= SKIP_OK) { if (skipChr(state, '?') >= SKIP_OK) { - token->type = TokCommonQueryProgramHeader; + token->type = SCPI_TOKEN_COMMON_QUERY_PROGRAM_HEADER; } else { - token->type = TokCommonProgramHeader; + token->type = SCPI_TOKEN_COMMON_PROGRAM_HEADER; } } else if (res <= SKIP_INCOMPLETE) { - token->type = TokIncompleteCommonProgramHeader; + token->type = SCPI_TOKEN_INCOMPLETE_COMMON_PROGRAM_HEADER; } else if (res == SKIP_NONE) { res = skipCompoundProgramHeader(state); if (res >= SKIP_OK) { if (skipChr(state, '?') >= SKIP_OK) { - token->type = TokCompoundQueryProgramHeader; + token->type = SCPI_TOKEN_COMPOUND_QUERY_PROGRAM_HEADER; } else { - token->type = TokCompoundProgramHeader; + token->type = SCPI_TOKEN_COMPOUND_PROGRAM_HEADER; } } else if (res <= SKIP_INCOMPLETE) { - token->type = TokIncompleteCompoundProgramHeader; - } + token->type = SCPI_TOKEN_INCOMPLETE_COMPOUND_PROGRAM_HEADER; + } } - if (token->type != TokUnknown) { + if (token->type != SCPI_TOKEN_UNKNOWN) { token->len = state->pos - token->ptr; } else { token->len = 0; @@ -309,6 +441,13 @@ } /* 7.7.1 <CHARACTER PROGRAM DATA> */ + +/** + * Detect token "Character program data" + * @param state + * @param token + * @return + */ int scpiLex_CharacterProgramData(lex_state_t * state, scpi_token_t * token) { token->ptr = state->pos; @@ -321,9 +460,9 @@ token->len = state->pos - token->ptr; if (token->len > 0) { - token->type = TokProgramMnemonic; + token->type = SCPI_TOKEN_PROGRAM_MNEMONIC; } else { - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; } return token->len; @@ -360,8 +499,14 @@ return someNumbers; } +/** + * Detect token Decimal number + * @param state + * @param token + * @return + */ int scpiLex_DecimalNumericProgramData(lex_state_t * state, scpi_token_t * token) { - const char * rollback; + char * rollback; token->ptr = state->pos; if (skipMantisa(state)) { @@ -376,9 +521,9 @@ token->len = state->pos - token->ptr; if (token->len > 0) { - token->type = TokDecimalNumericProgramData; + token->type = SCPI_TOKEN_DECIMAL_NUMERIC_PROGRAM_DATA; } else { - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; } return token->len; @@ -404,9 +549,9 @@ token->len = state->pos - token->ptr; if ((token->len > 0)) { - token->type = TokSuffixProgramData; + token->type = SCPI_TOKEN_SUFFIX_PROGRAM_DATA; } else { - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; state->pos = token->ptr; token->len = 0; } @@ -442,23 +587,29 @@ return someNumbers; } +/** + * Detect token nondecimal number + * @param state + * @param token + * @return + */ int scpiLex_NondecimalNumericData(lex_state_t * state, scpi_token_t * token) { - token->ptr = state->pos; int someNumbers = 0; + token->ptr = state->pos; if (skipChr(state, '#')) { if (!iseos(state)) { if (isH(state->pos[0])) { state->pos++; someNumbers = skipHexNum(state); - token->type = TokHexnum; + token->type = SCPI_TOKEN_HEXNUM; } else if (isQ(state->pos[0])) { state->pos++; someNumbers = skipOctNum(state); - token->type = TokOctnum; + token->type = SCPI_TOKEN_OCTNUM; } else if (isB(state->pos[0])) { state->pos++; someNumbers = skipBinNum(state); - token->type = TokBinnum; + token->type = SCPI_TOKEN_BINNUM; } } } @@ -467,7 +618,7 @@ token->ptr += 2; // ignore number prefix token->len = state->pos - token->ptr; } else { - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; state->pos = token->ptr; token->len = 0; } @@ -479,7 +630,7 @@ return (c >= 0) && (c <= 0x7f); } -static int skipQuoteProgramData(lex_state_t * state, int quote) { +static void skipQuoteProgramData(lex_state_t * state, char quote) { while (!iseos(state)) { if (isascii7bit(state->pos[0]) && !ischr(state, quote)) { state->pos++; @@ -495,21 +646,27 @@ } } -static int skipDoubleQuoteProgramData(lex_state_t * state) { +static void skipDoubleQuoteProgramData(lex_state_t * state) { skipQuoteProgramData(state, '"'); } -static int skipSingleQuoteProgramData(lex_state_t * state) { +static void skipSingleQuoteProgramData(lex_state_t * state) { skipQuoteProgramData(state, '\''); } +/** + * Detect token String data + * @param state + * @param token + * @return + */ int scpiLex_StringProgramData(lex_state_t * state, scpi_token_t * token) { token->ptr = state->pos; if (!iseos(state)) { if (ischr(state, '"')) { state->pos++; - token->type = TokDoubleQuoteProgramData; + token->type = SCPI_TOKEN_DOUBLE_QUOTE_PROGRAM_DATA; skipDoubleQuoteProgramData(state); if (!iseos(state) && ischr(state, '"')) { state->pos++; @@ -519,7 +676,7 @@ } } else if (ischr(state, '\'')) { state->pos++; - token->type = TokSingleQuoteProgramData; + token->type = SCPI_TOKEN_SINGLE_QUOTE_PROGRAM_DATA; skipSingleQuoteProgramData(state); if (!iseos(state) && ischr(state, '\'')) { state->pos++; @@ -536,7 +693,7 @@ token->ptr++; token->len -= 2; } else { - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; state->pos = token->ptr; token->len = 0; } @@ -549,10 +706,17 @@ return isdigit(c) && (c != '0'); } +/** + * Detect token Block Data + * @param state + * @param token + * @return + */ int scpiLex_ArbitraryBlockProgramData(lex_state_t * state, scpi_token_t * token) { int i; - int j = 0; + int arbitraryBlockLength = 0; const char * ptr = state->pos; + int validData = -1; token->ptr = state->pos; if (skipChr(state, '#')) { @@ -563,8 +727,8 @@ for (; i > 0; i--) { if (!iseos(state) && isdigit(state->pos[0])) { - j *= 10; - j += (state->pos[0] - '0'); + arbitraryBlockLength *= 10; + arbitraryBlockLength += (state->pos[0] - '0'); state->pos++; } else { break; @@ -572,25 +736,31 @@ } if (i == 0) { - state->pos += j; - if ((state->buffer + state->len) < (state->pos)) { - token->len = 0; - } else { - token->ptr = state->pos - j; - token->len = j; + state->pos += arbitraryBlockLength; + if ((state->buffer + state->len) >= (state->pos)) { + token->ptr = state->pos - arbitraryBlockLength; + token->len = arbitraryBlockLength; + validData = 1; } - } else { - token->len = 0; + } else if (iseos(state)) { + validData = 0; } - } else { - token->len = 0; + } else if (iseos(state)) { + validData = 0; } } - if ((token->len > 0)) { - token->type = TokArbitraryBlockProgramData; + if (validData == 1) { + // valid + token->type = SCPI_TOKEN_ARBITRARY_BLOCK_PROGRAM_DATA; + } else if (validData == 0) { + // incomplete + token->type = SCPI_TOKEN_UNKNOWN; + token->len = 0; + state->pos = state->buffer + state->len; } else { - token->type = TokUnknown; + // invalid + token->type = SCPI_TOKEN_UNKNOWN; state->pos = token->ptr; token->len = 0; } @@ -622,6 +792,12 @@ // TODO: 7.7.7.2-2 recursive - any program data +/** + * Detect token Expression + * @param state + * @param token + * @return + */ int scpiLex_ProgramExpression(lex_state_t * state, scpi_token_t * token) { token->ptr = state->pos; @@ -638,9 +814,9 @@ } if ((token->len > 0)) { - token->type = TokProgramExpression; + token->type = SCPI_TOKEN_PROGRAM_EXPRESSION; } else { - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; state->pos = token->ptr; token->len = 0; } @@ -648,34 +824,52 @@ return token->len; } +/** + * Detect token comma + * @param state + * @param token + * @return + */ int scpiLex_Comma(lex_state_t * state, scpi_token_t * token) { token->ptr = state->pos; if (skipChr(state, ',')) { token->len = 1; - token->type = TokComma; + token->type = SCPI_TOKEN_COMMA; } else { token->len = 0; - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; } return token->len; } +/** + * Detect token semicolon + * @param state + * @param token + * @return + */ int scpiLex_Semicolon(lex_state_t * state, scpi_token_t * token) { token->ptr = state->pos; if (skipChr(state, ';')) { token->len = 1; - token->type = TokSemicolon; + token->type = SCPI_TOKEN_SEMICOLON; } else { token->len = 0; - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; } return token->len; } +/** + * Detect token New line + * @param state + * @param token + * @return + */ int scpiLex_NewLine(lex_state_t * state, scpi_token_t * token) { token->ptr = state->pos; @@ -685,9 +879,9 @@ token->len = state->pos - token->ptr; if ((token->len > 0)) { - token->type = TokNewLine; + token->type = SCPI_TOKEN_NL; } else { - token->type = TokUnknown; + token->type = SCPI_TOKEN_UNKNOWN; state->pos = token->ptr; token->len = 0; } -- Gitblit v1.9.1