From 57c1983e07f24f7814e7d1985ab303ed2aca79ea Mon Sep 17 00:00:00 2001 From: Paul Beckingham Date: Sat, 22 Jan 2011 23:33:47 -0500 Subject: [PATCH] Code Migration - Migrated taskd JSON parser into task, to provide encode/decode capability to Task::composeJSON. - Migrated taskd utf8 code, replacing old unused code. - Added unit tests or JSON. - Migrated Tree updates from taskd. --- src/CMakeLists.txt | 6 +- src/JSON.cpp | 338 +++++++++++++++++++++++ src/JSON.h | 61 +++++ src/Nibbler.cpp | 14 +- src/Nibbler.h | 4 + src/Tree.cpp | 22 +- src/Tree.h | 2 + src/utf8.cpp | 640 +++++++++----------------------------------- src/utf8.h | 87 +----- test/.gitignore | 1 + test/CMakeLists.txt | 2 +- test/json.t.cpp | 145 ++++++++++ test/nibbler.t.cpp | 2 +- 13 files changed, 717 insertions(+), 607 deletions(-) create mode 100644 src/JSON.cpp create mode 100644 src/JSON.h create mode 100644 test/json.t.cpp diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index e1e731e15..49999e394 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -5,8 +5,8 @@ set (task_SRCS API.cpp API.h Att.cpp Att.h Cmd.cpp Cmd.h Color.cpp Color.h Config.cpp Config.h Context.cpp Context.h Date.cpp Date.h Directory.cpp Directory.h Duration.cpp Duration.h File.cpp File.h Filter.cpp Filter.h Grid.cpp Grid.h Hooks.cpp Hooks.h - Keymap.cpp Keymap.h Lisp.cpp Lisp.h Location.cpp Location.h - Nibbler.cpp Nibbler.h Path.cpp Path.h Permission.cpp + JSON.cpp JSON.h Keymap.cpp Keymap.h Lisp.cpp Lisp.h Location.cpp + Location.h Nibbler.cpp Nibbler.h Path.cpp Path.h Permission.cpp Permission.h Record.cpp Record.h Rectangle.cpp Rectangle.h Sensor.cpp Sensor.h Sequence.cpp Sequence.h StringTable.cpp StringTable.h Subst.cpp Subst.h TDB.cpp TDB.h Table.cpp Table.h @@ -17,7 +17,7 @@ set (task_SRCS API.cpp API.h Att.cpp Att.h Cmd.cpp Cmd.h Color.cpp Color.h command.cpp custom.cpp dependency.cpp diag.cpp edit.cpp export.cpp history.cpp i18n.h import.cpp interactive.cpp recur.cpp report.cpp rules.cpp rx.cpp rx.h text.cpp text.h - util.cpp util.h Uri.cpp Uri.h) + utf8.cpp utf8.h util.cpp util.h Uri.cpp Uri.h) add_library (task STATIC ${task_SRCS}) add_executable (task_executable main.cpp) diff --git a/src/JSON.cpp b/src/JSON.cpp new file mode 100644 index 000000000..925d17fc2 --- /dev/null +++ b/src/JSON.cpp @@ -0,0 +1,338 @@ +//////////////////////////////////////////////////////////////////////////////// +// taskwarrior - a command line task list manager. +// +// Copyright 2010 - 2011, Paul Beckingham, Federico Hernandez. +// All rights reserved. +// +// 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 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 +// +//////////////////////////////////////////////////////////////////////////////// + +#include +#include +#include +#include + +//////////////////////////////////////////////////////////////////////////////// +JSON::JSON () +: root ("root") +{ +} + +//////////////////////////////////////////////////////////////////////////////// +JSON::JSON (const std::string& input) +: root ("root") +{ + Nibbler n (input); + if (!parseObject (&root, n)) + throw std::string ("Syntax error in request."); +} + +//////////////////////////////////////////////////////////////////////////////// +JSON::~JSON () +{ +} + +//////////////////////////////////////////////////////////////////////////////// +// \n -> "\\n" +// \t -> "\\t" +std::string JSON::encode (const std::string& input) +{ + std::string output; + + for (std::string::size_type i = 0; i < input.length (); ++i) + { + switch (input[i]) + { + // Simple translations. + case '"': output += "\\\""; break; + case '\\': output += "\\\\"; break; + case '/': output += "\\/"; break; + case '\b': output += "\\b"; break; + case '\f': output += "\\f"; break; + case '\n': output += "\\n"; break; + case '\r': output += "\\r"; break; + case '\t': output += "\\t"; break; + + // Default NOP. + default: output += input[i]; break; + } + } + + return output; +} + +//////////////////////////////////////////////////////////////////////////////// +std::string JSON::decode (const std::string& input) +{ + std::string output; + + for (unsigned int i = 0; i < input.length (); ++i) + { + if (input[i] == '\\') + { + ++i; + switch (input[i]) + { + // Simple translations. + case '"': output += '"'; break; + case '\\': output += '\\'; break; + case '/': output += '/'; break; + case 'b': output += '\b'; break; + case 'f': output += '\f'; break; + case 'n': output += '\n'; break; + case 'r': output += '\r'; break; + case 't': output += '\t'; break; + + // Compose a UTF8 unicode character. + case 'u': + output += utf8_character (utf8_codepoint (input.substr (++i))); + i += 3; + break; + + // If it is an unrecognized seqeence, do nothing. + default: + output += '\\'; + output += input[i]; + break; + } + } + else + output += input[i]; + } + + return output; +} + +//////////////////////////////////////////////////////////////////////////////// +Tree* JSON::tree () +{ + return &root; +} + +//////////////////////////////////////////////////////////////////////////////// +// object +// {} +// { pair , ... } +bool JSON::parseObject (Tree* t, Nibbler& nibbler) +{ + Nibbler n (nibbler); + n.skipWS (); + + if (n.skip ('{')) + { + n.skipWS (); + + Tree* node = new Tree ("node"); + if (parsePair (node, n)) + { + t->addBranch (node); + + n.skipWS (); + while (n.skip (',')) + { + n.skipWS (); + + node = new Tree ("node"); + if (!parsePair (node, n)) + { + delete node; + return false; + } + + t->addBranch (node); + n.skipWS (); + } + } + else + delete node; + + if (n.skip ('}')) + { + n.skipWS (); + nibbler = n; + t->attribute ("type", "collection"); + return true; + } + } + + return false; +} + +//////////////////////////////////////////////////////////////////////////////// +// pair +// string : value +bool JSON::parsePair (Tree* t, Nibbler& nibbler) +{ + Nibbler n (nibbler); + + std::string value; + if (n.getQuoted ('"', value)) + { + n.skipWS (); + if (n.skip (':')) + { + n.skipWS (); + if (parseValue (t, n)) + { + nibbler = n; + t->name (value); + return true; + } + } + } + + return false; +} + +//////////////////////////////////////////////////////////////////////////////// +// array +// [] +// [ value , ... ] +bool JSON::parseArray (Tree* t, Nibbler& nibbler) +{ + Nibbler n (nibbler); + n.skipWS (); + + if (n.skip ('[')) + { + n.skipWS (); + + Tree* node = new Tree ("node"); + if (parseValue (node, n)) + { + t->addBranch (node); + + n.skipWS (); + while (n.skip (',')) + { + n.skipWS (); + + node = new Tree ("node"); + if (!parseValue (node, n)) + { + delete node; + return false; + } + + t->addBranch (node); + n.skipWS (); + } + } + else + delete node; + + if (n.skip (']')) + { + n.skipWS (); + nibbler = n; + t->attribute ("type", "list"); + return true; + } + } + + return false; +} + +//////////////////////////////////////////////////////////////////////////////// +// value +// string +// number +// object +// array +// true +// false +// null +bool JSON::parseValue (Tree* t, Nibbler& nibbler) +{ + if (parseString (t, nibbler) || + parseNumber (t, nibbler) || + parseObject (t, nibbler) || + parseArray (t, nibbler) || + nibbler.getLiteral ("true") || + nibbler.getLiteral ("false") || + nibbler.getLiteral ("null")) + { + return true; + } + + return false; +} + +//////////////////////////////////////////////////////////////////////////////// +// string +// "" +// " chars " +// +// chars +// char +// char chars +// +// char +// any-Unicode-character-except-"-or-\-or-control-character +// \" +// \\ [extra text to de-confuse gcc] +// \/ +// \b +// \f +// \n +// \r +// \t +// \u four-hex-digits +bool JSON::parseString (Tree* t, Nibbler& nibbler) +{ + std::string value; + if (nibbler.getQuoted ('"', value, false)) + { + t->attribute ("type", "string"); + t->attribute ("value", value); + return true; + } + + return false; +} + +//////////////////////////////////////////////////////////////////////////////// +// number +// int frac exp +// int frac +// int exp +// int +bool JSON::parseNumber (Tree* t, Nibbler& nibbler) +{ + int i; + double d; + if (nibbler.getNumber (d)) + { + t->attribute ("type", "number"); + t->attribute ("value", d); + return true; + } + else if (nibbler.getInt (i)) + { + t->attribute ("type", "number"); + t->attribute ("value", i); + return true; + } + + return false; +} + +//////////////////////////////////////////////////////////////////////////////// diff --git a/src/JSON.h b/src/JSON.h new file mode 100644 index 000000000..de37e6305 --- /dev/null +++ b/src/JSON.h @@ -0,0 +1,61 @@ +//////////////////////////////////////////////////////////////////////////////// +// taskwarrior - a command line task list manager. +// +// Copyright 2010 - 2011, Paul Beckingham, Federico Hernandez. +// All rights reserved. +// +// 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 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 +// +//////////////////////////////////////////////////////////////////////////////// +#ifndef INCLUDED_JSON +#define INCLUDED_JSON + +#include +#include +#include + +class JSON +{ +public: + JSON (); // Default constructor + JSON (const std::string&); // Constructor + JSON (const JSON&); // Copy constructor + JSON& operator= (const JSON&); // Assignment operator + ~JSON (); // Destructor + + static std::string encode (const std::string&); + static std::string decode (const std::string&); + + Tree* tree (); + +private: + bool parseObject (Tree*, Nibbler&); + bool parsePair (Tree*, Nibbler&); + bool parseArray (Tree*, Nibbler&); + bool parseValue (Tree*, Nibbler&); + bool parseString (Tree*, Nibbler&); + bool parseNumber (Tree*, Nibbler&); + +private: + Tree root; +}; + +#endif +//////////////////////////////////////////////////////////////////////////////// diff --git a/src/Nibbler.cpp b/src/Nibbler.cpp index 7529422d2..541d8871d 100644 --- a/src/Nibbler.cpp +++ b/src/Nibbler.cpp @@ -26,11 +26,11 @@ //////////////////////////////////////////////////////////////////////////////// #include -#include #include #include -#include "Nibbler.h" -#include "rx.h" +#include +#include +#include const char* c_digits = "0123456789"; @@ -283,7 +283,7 @@ bool Nibbler::getInt (int& result) if (i > mCursor) { - result = atoi (mInput.substr (mCursor, i - mCursor).c_str ()); + result = strtoimax (mInput.substr (mCursor, i - mCursor).c_str (), NULL, 10); mCursor = i; return true; } @@ -328,7 +328,7 @@ bool Nibbler::getUnsignedInt (int& result) if (i > mCursor) { - result = atoi (mInput.substr (mCursor, i - mCursor).c_str ()); + result = strtoimax (mInput.substr (mCursor, i - mCursor).c_str (), NULL, 10); mCursor = i; return true; } @@ -392,7 +392,7 @@ bool Nibbler::getNumber (double& result) while (i < mLength && isdigit (mInput[i])) ++i; - result = atof (mInput.substr (mCursor, i - mCursor).c_str ()); + result = strtof (mInput.substr (mCursor, i - mCursor).c_str (), NULL); mCursor = i; return true; } @@ -400,7 +400,7 @@ bool Nibbler::getNumber (double& result) return false; } - result = atof (mInput.substr (mCursor, i - mCursor).c_str ()); + result = strtof (mInput.substr (mCursor, i - mCursor).c_str (), NULL); mCursor = i; return true; } diff --git a/src/Nibbler.h b/src/Nibbler.h index d570aff1e..604ae177d 100644 --- a/src/Nibbler.h +++ b/src/Nibbler.h @@ -47,6 +47,10 @@ public: bool getUntilEOL (std::string&); bool getUntilEOS (std::string&); +/* + bool getAllOneOf (const std::string&, std::string&); +*/ + bool getQuoted (char, std::string&, bool quote = false); bool getInt (int&); bool getHex (int&); diff --git a/src/Tree.cpp b/src/Tree.cpp index 4ceb98c0d..3068fac72 100644 --- a/src/Tree.cpp +++ b/src/Tree.cpp @@ -27,9 +27,8 @@ #include #include -#include -#include "text.h" -#include "Tree.h" +#include +#include //////////////////////////////////////////////////////////////////////////////// // - Tree, Branch and Node are synonymous. @@ -118,6 +117,12 @@ int Tree::branches () return _branches.size (); } +//////////////////////////////////////////////////////////////////////////////// +void Tree::name (const std::string& name) +{ + _name = name; +} + //////////////////////////////////////////////////////////////////////////////// std::string Tree::name () const { @@ -135,9 +140,14 @@ void Tree::attribute (const std::string& name, const std::string& value) // Accessor for attributes. void Tree::attribute (const std::string& name, const int value) { - std::stringstream s; - s << value; - _attributes[name] = s.str (); + _attributes[name] = format (value); +} + +//////////////////////////////////////////////////////////////////////////////// +// Accessor for attributes. +void Tree::attribute (const std::string& name, const double value) +{ + _attributes[name] = format (value, 1, 8); } //////////////////////////////////////////////////////////////////////////////// diff --git a/src/Tree.h b/src/Tree.h index d0adbd635..65d70a97e 100644 --- a/src/Tree.h +++ b/src/Tree.h @@ -47,9 +47,11 @@ public: void replaceBranch (Tree*, Tree*); int branches (); + void name (const std::string&); std::string name () const; void attribute (const std::string&, const std::string&); void attribute (const std::string&, const int); + void attribute (const std::string&, const double); std::string attribute (const std::string&); void removeAttribute (const std::string&); int attributes () const; diff --git a/src/utf8.cpp b/src/utf8.cpp index 82db7b675..6d059a679 100644 --- a/src/utf8.cpp +++ b/src/utf8.cpp @@ -1,486 +1,7 @@ -#ifdef NOPE -/* - Basic UTF-8 manipulation routines - by Jeff Bezanson - placed in the public domain Fall 2005 - - This code is designed to provide the utilities you need to manipulate - UTF-8 as an internal string encoding. These functions do not perform the - error checking normally needed when handling UTF-8 data, so if you happen - to be from the Unicode Consortium you will want to flay me alive. - I do this because error checking can be performed at the boundaries (I/O), - with these routines reserved for higher performance on data known to be - valid. -*/ -#include -#include -#include -#include -#ifdef WIN32 -#include -#else -#include -#endif - -#include "utf8.h" - -static const u_int32_t offsetsFromUTF8[6] = { - 0x00000000UL, 0x00003080UL, 0x000E2080UL, - 0x03C82080UL, 0xFA082080UL, 0x82082080UL -}; - -static const char trailingBytesForUTF8[256] = { - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 -}; - -/* returns length of next utf-8 sequence */ -int u8_seqlen(char *s) -{ - return trailingBytesForUTF8[(unsigned int)(unsigned char)s[0]] + 1; -} - -/* conversions without error checking - only works for valid UTF-8, i.e. no 5- or 6-byte sequences - srcsz = source size in bytes, or -1 if 0-terminated - sz = dest size in # of wide characters - - returns # characters converted - dest will always be L'\0'-terminated, even if there isn't enough room - for all the characters. - if sz = srcsz+1 (i.e. 4*srcsz+4 bytes), there will always be enough space. -*/ -int u8_toucs(u_int32_t *dest, int sz, char *src, int srcsz) -{ - u_int32_t ch; - char *src_end = src + srcsz; - int nb; - int i=0; - - while (i < sz-1) { - nb = trailingBytesForUTF8[(unsigned char)*src]; - if (srcsz == -1) { - if (*src == 0) - goto done_toucs; - } - else { - if (src + nb >= src_end) - goto done_toucs; - } - ch = 0; - switch (nb) { - /* these fall through deliberately */ - case 3: ch += (unsigned char)*src++; ch <<= 6; - case 2: ch += (unsigned char)*src++; ch <<= 6; - case 1: ch += (unsigned char)*src++; ch <<= 6; - case 0: ch += (unsigned char)*src++; - } - ch -= offsetsFromUTF8[nb]; - dest[i++] = ch; - } - done_toucs: - dest[i] = 0; - return i; -} - -/* srcsz = number of source characters, or -1 if 0-terminated - sz = size of dest buffer in bytes - - returns # characters converted - dest will only be '\0'-terminated if there is enough space. this is - for consistency; imagine there are 2 bytes of space left, but the next - character requires 3 bytes. in this case we could NUL-terminate, but in - general we can't when there's insufficient space. therefore this function - only NUL-terminates if all the characters fit, and there's space for - the NUL as well. - the destination string will never be bigger than the source string. -*/ -int u8_toutf8(char *dest, int sz, u_int32_t *src, int srcsz) -{ - u_int32_t ch; - int i = 0; - char *dest_end = dest + sz; - - while (srcsz<0 ? src[i]!=0 : i < srcsz) { - ch = src[i]; - if (ch < 0x80) { - if (dest >= dest_end) - return i; - *dest++ = (char)ch; - } - else if (ch < 0x800) { - if (dest >= dest_end-1) - return i; - *dest++ = (ch>>6) | 0xC0; - *dest++ = (ch & 0x3F) | 0x80; - } - else if (ch < 0x10000) { - if (dest >= dest_end-2) - return i; - *dest++ = (ch>>12) | 0xE0; - *dest++ = ((ch>>6) & 0x3F) | 0x80; - *dest++ = (ch & 0x3F) | 0x80; - } - else if (ch < 0x110000) { - if (dest >= dest_end-3) - return i; - *dest++ = (ch>>18) | 0xF0; - *dest++ = ((ch>>12) & 0x3F) | 0x80; - *dest++ = ((ch>>6) & 0x3F) | 0x80; - *dest++ = (ch & 0x3F) | 0x80; - } - i++; - } - if (dest < dest_end) - *dest = '\0'; - return i; -} - -int u8_wc_toutf8(char *dest, u_int32_t ch) -{ - if (ch < 0x80) { - dest[0] = (char)ch; - return 1; - } - if (ch < 0x800) { - dest[0] = (ch>>6) | 0xC0; - dest[1] = (ch & 0x3F) | 0x80; - return 2; - } - if (ch < 0x10000) { - dest[0] = (ch>>12) | 0xE0; - dest[1] = ((ch>>6) & 0x3F) | 0x80; - dest[2] = (ch & 0x3F) | 0x80; - return 3; - } - if (ch < 0x110000) { - dest[0] = (ch>>18) | 0xF0; - dest[1] = ((ch>>12) & 0x3F) | 0x80; - dest[2] = ((ch>>6) & 0x3F) | 0x80; - dest[3] = (ch & 0x3F) | 0x80; - return 4; - } - return 0; -} - -/* charnum => byte offset */ -int u8_offset(char *str, int charnum) -{ - int offs=0; - - while (charnum > 0 && str[offs]) { - (void)(isutf(str[++offs]) || isutf(str[++offs]) || - isutf(str[++offs]) || ++offs); - charnum--; - } - return offs; -} - -/* byte offset => charnum */ -int u8_charnum(char *s, int offset) -{ - int charnum = 0, offs=0; - - while (offs < offset && s[offs]) { - (void)(isutf(s[++offs]) || isutf(s[++offs]) || - isutf(s[++offs]) || ++offs); - charnum++; - } - return charnum; -} - -/* number of characters */ -int u8_strlen(char *s) -{ - int count = 0; - int i = 0; - - while (u8_nextchar(s, &i) != 0) - count++; - - return count; -} - -/* reads the next utf-8 sequence out of a string, updating an index */ -u_int32_t u8_nextchar(char *s, int *i) -{ - u_int32_t ch = 0; - int sz = 0; - - do { - ch <<= 6; - ch += (unsigned char)s[(*i)++]; - sz++; - } while (s[*i] && !isutf(s[*i])); - ch -= offsetsFromUTF8[sz-1]; - - return ch; -} - -void u8_inc(char *s, int *i) -{ - (void)(isutf(s[++(*i)]) || isutf(s[++(*i)]) || - isutf(s[++(*i)]) || ++(*i)); -} - -void u8_dec(char *s, int *i) -{ - (void)(isutf(s[--(*i)]) || isutf(s[--(*i)]) || - isutf(s[--(*i)]) || --(*i)); -} - -int octal_digit(char c) -{ - return (c >= '0' && c <= '7'); -} - -int hex_digit(char c) -{ - return ((c >= '0' && c <= '9') || - (c >= 'A' && c <= 'F') || - (c >= 'a' && c <= 'f')); -} - -/* assumes that src points to the character after a backslash - returns number of input characters processed */ -int u8_read_escape_sequence(char *str, u_int32_t *dest) -{ - u_int32_t ch; - char digs[9]="\0\0\0\0\0\0\0\0"; - int dno=0, i=1; - - ch = (u_int32_t)str[0]; /* take literal character */ - if (str[0] == 'n') - ch = L'\n'; - else if (str[0] == 't') - ch = L'\t'; - else if (str[0] == 'r') - ch = L'\r'; - else if (str[0] == 'b') - ch = L'\b'; - else if (str[0] == 'f') - ch = L'\f'; - else if (str[0] == 'v') - ch = L'\v'; - else if (str[0] == 'a') - ch = L'\a'; - else if (octal_digit(str[0])) { - i = 0; - do { - digs[dno++] = str[i++]; - } while (octal_digit(str[i]) && dno < 3); - ch = strtol(digs, NULL, 8); - } - else if (str[0] == 'x') { - while (hex_digit(str[i]) && dno < 2) { - digs[dno++] = str[i++]; - } - if (dno > 0) - ch = strtol(digs, NULL, 16); - } - else if (str[0] == 'u') { - while (hex_digit(str[i]) && dno < 4) { - digs[dno++] = str[i++]; - } - if (dno > 0) - ch = strtol(digs, NULL, 16); - } - else if (str[0] == 'U') { - while (hex_digit(str[i]) && dno < 8) { - digs[dno++] = str[i++]; - } - if (dno > 0) - ch = strtol(digs, NULL, 16); - } - *dest = ch; - - return i; -} - -/* convert a string with literal \uxxxx or \Uxxxxxxxx characters to UTF-8 - example: u8_unescape(mybuf, 256, "hello\\u220e") - note the double backslash is needed if called on a C string literal */ -int u8_unescape(char *buf, int sz, char *src) -{ - int c=0, amt; - u_int32_t ch; - char temp[4]; - - while (*src && c < sz) { - if (*src == '\\') { - src++; - amt = u8_read_escape_sequence(src, &ch); - } - else { - ch = (u_int32_t)*src; - amt = 1; - } - src += amt; - amt = u8_wc_toutf8(temp, ch); - if (amt > sz-c) - break; - memcpy(&buf[c], temp, amt); - c += amt; - } - if (c < sz) - buf[c] = '\0'; - return c; -} - -int u8_escape_wchar(char *buf, int sz, u_int32_t ch) -{ - if (ch == L'\n') - return snprintf(buf, sz, "\\n"); - else if (ch == L'\t') - return snprintf(buf, sz, "\\t"); - else if (ch == L'\r') - return snprintf(buf, sz, "\\r"); - else if (ch == L'\b') - return snprintf(buf, sz, "\\b"); - else if (ch == L'\f') - return snprintf(buf, sz, "\\f"); - else if (ch == L'\v') - return snprintf(buf, sz, "\\v"); - else if (ch == L'\a') - return snprintf(buf, sz, "\\a"); - else if (ch == L'\\') - return snprintf(buf, sz, "\\\\"); - else if (ch < 32 || ch == 0x7f) - return snprintf(buf, sz, "\\x%hhX", (unsigned char)ch); - else if (ch > 0xFFFF) - return snprintf(buf, sz, "\\U%.8X", (u_int32_t)ch); - else if (ch >= 0x80 && ch <= 0xFFFF) - return snprintf(buf, sz, "\\u%.4hX", (unsigned short)ch); - - return snprintf(buf, sz, "%c", (char)ch); -} - -int u8_escape(char *buf, int sz, char *src, int escape_quotes) -{ - int c=0, i=0, amt; - - while (src[i] && c < sz) { - if (escape_quotes && src[i] == '"') { - amt = snprintf(buf, sz - c, "\\\""); - i++; - } - else { - amt = u8_escape_wchar(buf, sz - c, u8_nextchar(src, &i)); - } - c += amt; - buf += amt; - } - if (c < sz) - *buf = '\0'; - return c; -} - -char *u8_strchr(char *s, u_int32_t ch, int *charn) -{ - int i = 0, lasti=0; - u_int32_t c; - - *charn = 0; - while (s[i]) { - c = u8_nextchar(s, &i); - if (c == ch) { - return &s[lasti]; - } - lasti = i; - (*charn)++; - } - return NULL; -} - -char *u8_memchr(char *s, u_int32_t ch, size_t sz, int *charn) -{ - int i = 0, lasti=0; - u_int32_t c; - int csz; - - *charn = 0; - while (i < sz) { - c = csz = 0; - do { - c <<= 6; - c += (unsigned char)s[i++]; - csz++; - } while (i < sz && !isutf(s[i])); - c -= offsetsFromUTF8[csz-1]; - - if (c == ch) { - return &s[lasti]; - } - lasti = i; - (*charn)++; - } - return NULL; -} - -int u8_is_locale_utf8(char *locale) -{ - /* this code based on libutf8 */ - const char* cp = locale; - - for (; *cp != '\0' && *cp != '@' && *cp != '+' && *cp != ','; cp++) { - if (*cp == '.') { - const char* encoding = ++cp; - for (; *cp != '\0' && *cp != '@' && *cp != '+' && *cp != ','; cp++) - ; - if ((cp-encoding == 5 && !strncmp(encoding, "UTF-8", 5)) - || (cp-encoding == 4 && !strncmp(encoding, "utf8", 4))) - return 1; /* it's UTF-8 */ - break; - } - } - return 0; -} - -int u8_vprintf(char *fmt, va_list ap) -{ - int cnt, sz=0; - char *buf; - u_int32_t *wcs; - - sz = 512; - buf = (char*)alloca(sz); - try_print: - cnt = vsnprintf(buf, sz, fmt, ap); - if (cnt >= sz) { - buf = (char*)alloca(cnt - sz + 1); - sz = cnt + 1; - goto try_print; - } - wcs = (u_int32_t*)alloca((cnt+1) * sizeof(u_int32_t)); - cnt = u8_toucs(wcs, cnt+1, buf, cnt); - printf("%ls", (wchar_t*)wcs); - return cnt; -} - -int u8_printf(char *fmt, ...) -{ - int cnt; - va_list args; - - va_start(args, fmt); - - cnt = u8_vprintf(fmt, args); - - va_end(args); - return cnt; -} -#endif - //////////////////////////////////////////////////////////////////////////////// // taskwarrior - a command line task list manager. // -// Copyright 2006 - 2011, Paul Beckingham, Federico Hernandez. +// Copyright 2010 - 2011, Paul Beckingham, Federico Hernandez. // All rights reserved. // // This program is free software; you can redistribute it and/or modify it under @@ -504,42 +25,145 @@ int u8_printf(char *fmt, ...) // //////////////////////////////////////////////////////////////////////////////// -#include "utf8.h" - -static const u_int32_t offsetsFromUTF8[6] = -{ - 0x00000000UL, 0x00003080UL, 0x000E2080UL, - 0x03C82080UL, 0xFA082080UL, 0x82082080UL, -}; +#include +#include //////////////////////////////////////////////////////////////////////////////// -// number of characters in a string. -int utf8_length (const std::string& s) -{ - int count = 0; - int i = 0; - - while (utf8_nextchar (s.c_str (), &i) != 0) - count++; - - return count; -} +// Converts '0' -> 0 +// '9' -> 9 +// 'a'/'A' -> 10 +// 'f'/'F' -> 15 +#define XDIGIT(x) ((x) >= '0' && (x) <= '9' ? ((x) - '0') : \ + (x) >= 'a' && (x) <= 'f' ? ((x) + 10 - 'a') : \ + (x) >= 'A' && (x) <= 'F' ? ((x) + 10 - 'A') : 0) //////////////////////////////////////////////////////////////////////////////// -// reads the next utf-8 sequence out of a string, updating an index. -u_int32_t utf8_nextchar (const char* s, int* i) +// Note: Assumes 4-digit hex codepoints: +// xxxx +// \uxxxx +// U+xxxx +unsigned int utf8_codepoint (const std::string& input) { - u_int32_t ch = 0; - int sz = 0; + unsigned int codepoint = 0; + int length = input.length (); - do + // U+xxxx, \uxxxx + if (length >= 6 && + ((input[0] == 'U' && input[1] == '+') || + (input[0] == '\\' && input[1] == 'u'))) { - ch <<= 6; - ch += (unsigned char) s[(*i)++]; - sz++; + codepoint = XDIGIT (input[2]) << 12 | + XDIGIT (input[3]) << 8 | + XDIGIT (input[4]) << 4 | + XDIGIT (input[5]); } - while (s[*i] && ! isutf (s[*i])); + else if (length >= 4) + { + codepoint = XDIGIT (input[0]) << 12 | + XDIGIT (input[1]) << 8 | + XDIGIT (input[2]) << 4 | + XDIGIT (input[3]); + } + else + throw std::string ("Invalid codepoint representation."); - return ch - offsetsFromUTF8[sz - 1]; + return codepoint; } +//////////////////////////////////////////////////////////////////////////////// +// Iterates along a UTF8 string. +unsigned int utf8_next_char (const std::string& input, std::string::size_type& i) +{ + // How many bytes in the sequence? + int length = utf8_sequence (input[i]); + + // 0xxxxxxx -> 0xxxxxxx + if (length == 1) + return input[i++]; + + // 110yyyyy 10xxxxxx -> 00000yyy yyxxxxxx + if (length == 2) + return ((input[i++] & 0x1F) << 6) + + (input[i++] & 0x3F); + + // 1110zzzz 10yyyyyy 10xxxxxx -> zzzzyyyy yyxxxxxx + if (length == 3) + return ((input[i++] & 0xF) << 12) + + ((input[i++] & 0x3F) << 6) + + (input[i++] & 0x3F); + + // 11110www 10zzzzzz 10yyyyyy 10xxxxxx -> 000wwwzz zzzzyyyy yyxxxxxx + if (length == 4) + return ((input[i++] & 0x7) << 18) + + ((input[i++] & 0x3F) << 12) + + ((input[i++] & 0x3F) << 6) + + (input[i++] & 0x3F); + + + // Default: pretend as though it's a single character. + // TODO Or should this throw? + return input[i++]; +} + +//////////////////////////////////////////////////////////////////////////////// +// http://en.wikipedia.org/wiki/UTF-8 +std::string utf8_character (unsigned int codepoint) +{ + char sequence[5]; + + // 0xxxxxxx -> 0xxxxxxx + if (codepoint < 0x80) + { + sequence[0] = codepoint; + sequence[1] = 0; + } + + // 00000yyy yyxxxxxx -> 110yyyyy 10xxxxxx + else if (codepoint < 0x800) + { + sequence[0] = 0xC0 | (codepoint & 0x7C0) >> 6; + sequence[1] = 0x80 | (codepoint & 0x3F); + sequence[2] = 0; + } + + // zzzzyyyy yyxxxxxx -> 1110zzzz 10yyyyyy 10xxxxxx + else if (codepoint < 0x10000) + { + sequence[0] = 0xE0 | (codepoint & 0xF000) >> 12; + sequence[1] = 0x80 | (codepoint & 0xFC0) >> 6; + sequence[2] = 0x80 | (codepoint & 0x3F); + sequence[3] = 0; + } + + // 000wwwzz zzzzyyyy yyxxxxxx -> 11110www 10zzzzzz 10yyyyyy 10xxxxxx + else if (codepoint < 0x110000) + { + sequence[0] = 0xF0 | (codepoint & 0x1C0000) >> 18; + sequence[1] = 0x80 | (codepoint & 0x03F000) >> 12; + sequence[2] = 0x80 | (codepoint & 0x0FC0) >> 6; + sequence[3] = 0x80 | (codepoint & 0x3F); + sequence[4] = 0; + } + else + throw std::string ("Invalid Unicode codepoint."); + + sequence[4] = '\0'; + return std::string (sequence); +} + +//////////////////////////////////////////////////////////////////////////////// +int utf8_sequence (unsigned int character) +{ + if ((character & 0xE0) == 0xC0) + return 2; + + if ((character & 0xF0) == 0xE0) + return 3; + + if ((character & 0xF8) == 0xF0) + return 4; + + return 1; +} + +//////////////////////////////////////////////////////////////////////////////// diff --git a/src/utf8.h b/src/utf8.h index 52b59d0e6..09aa49561 100644 --- a/src/utf8.h +++ b/src/utf8.h @@ -1,81 +1,7 @@ -#ifdef NOPE -#include - -/* is c the start of a utf8 sequence? */ -#define isutf(c) (((c)&0xC0)!=0x80) - -/* convert UTF-8 data to wide character */ -int u8_toucs(u_int32_t *dest, int sz, char *src, int srcsz); - -/* the opposite conversion */ -int u8_toutf8(char *dest, int sz, u_int32_t *src, int srcsz); - -/* single character to UTF-8 */ -int u8_wc_toutf8(char *dest, u_int32_t ch); - -/* character number to byte offset */ -int u8_offset(char *str, int charnum); - -/* byte offset to character number */ -int u8_charnum(char *s, int offset); - -/* return next character, updating an index variable */ -u_int32_t u8_nextchar(char *s, int *i); - -/* move to next character */ -void u8_inc(char *s, int *i); - -/* move to previous character */ -void u8_dec(char *s, int *i); - -/* returns length of next utf-8 sequence */ -int u8_seqlen(char *s); - -/* assuming src points to the character after a backslash, read an - escape sequence, storing the result in dest and returning the number of - input characters processed */ -int u8_read_escape_sequence(char *src, u_int32_t *dest); - -/* given a wide character, convert it to an ASCII escape sequence stored in - buf, where buf is "sz" bytes. returns the number of characters output. */ -int u8_escape_wchar(char *buf, int sz, u_int32_t ch); - -/* convert a string "src" containing escape sequences to UTF-8 */ -int u8_unescape(char *buf, int sz, char *src); - -/* convert UTF-8 "src" to ASCII with escape sequences. - if escape_quotes is nonzero, quote characters will be preceded by - backslashes as well. */ -int u8_escape(char *buf, int sz, char *src, int escape_quotes); - -/* utility predicates used by the above */ -int octal_digit(char c); -int hex_digit(char c); - -/* return a pointer to the first occurrence of ch in s, or NULL if not - found. character index of found character returned in *charn. */ -char *u8_strchr(char *s, u_int32_t ch, int *charn); - -/* same as the above, but searches a buffer of a given size instead of - a NUL-terminated string. */ -char *u8_memchr(char *s, u_int32_t ch, size_t sz, int *charn); - -/* count the number of characters in a UTF-8 string */ -int u8_strlen(char *s); - -int u8_is_locale_utf8(char *locale); - -/* printf where the format string and arguments may be in UTF-8. - you can avoid this function and just use ordinary printf() if the current - locale is UTF-8. */ -int u8_vprintf(char *fmt, va_list ap); -int u8_printf(char *fmt, ...); -#endif - //////////////////////////////////////////////////////////////////////////////// // taskwarrior - a command line task list manager. // -// Copyright 2006 - 2011, Paul Beckingham, Federico Hernandez. +// Copyright 2010 - 2011, Paul Beckingham, Federico Hernandez. // All rights reserved. // // This program is free software; you can redistribute it and/or modify it under @@ -103,11 +29,10 @@ int u8_printf(char *fmt, ...); #include -// is c the start of a utf8 sequence? -#define isutf(c) (((c)&0xC0)!=0x80) - -int utf8_length (const std::string&); -u_int32_t utf8_nextchar (const char*, int*); +unsigned int utf8_codepoint (const std::string&); +unsigned int utf8_next_char (const std::string&, std::string::size_type&); +std::string utf8_character (unsigned int); +int utf8_sequence (unsigned int); #endif - +//////////////////////////////////////////////////////////////////////////////// diff --git a/test/.gitignore b/test/.gitignore index f6ca1b77b..2a20631eb 100644 --- a/test/.gitignore +++ b/test/.gitignore @@ -11,6 +11,7 @@ duration.t file.t filt.t grid.t +json.t lisp.t list.t nibbler.t diff --git a/test/CMakeLists.txt b/test/CMakeLists.txt index e9d6b5022..7c2beb2e4 100644 --- a/test/CMakeLists.txt +++ b/test/CMakeLists.txt @@ -6,7 +6,7 @@ include_directories (${CMAKE_SOURCE_DIR}/src set (test_SRCS date.t t.t tdb.t duration.t t.benchmark.t text.t autocomplete.t seq.t record.t att.t stringtable.t subst.t nibbler.t filt.t cmd.t config.t util.t color.t list.t path.t file.t grid.t directory.t rx.t taskmod.t - lisp.t rectangle.t sensor.t tree.t tree2.t uri.t) + lisp.t rectangle.t sensor.t tree.t tree2.t uri.t json.t) add_custom_target (test ./run_all DEPENDS ${test_SRCS} WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}/test) diff --git a/test/json.t.cpp b/test/json.t.cpp new file mode 100644 index 000000000..268b53907 --- /dev/null +++ b/test/json.t.cpp @@ -0,0 +1,145 @@ +//////////////////////////////////////////////////////////////////////////////// +// taskwarrior - a command line task list manager. +// +// Copyright 2006 - 2011, Paul Beckingham. +// All rights reserved. +// +// 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 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 +// +//////////////////////////////////////////////////////////////////////////////// + +#include +#include +#include +#include + +Context context; + +//////////////////////////////////////////////////////////////////////////////// +int main (int argc, char** argv) +{ + UnitTest t (14); + + try + { + // Basic parsing tests. + std::string input = "{}"; + std::cout << "-- j1 -------------------\n" + << "input: " << input << "\n"; + JSON j1 (input); + j1.tree ()->dump (); + + input = "{\"name\":123}"; + std::cout << "-- j2 -------------------\n" + << "input: " << input << "\n"; + JSON j2 (input); + j2.tree ()->dump (); + + input = "{\"name\":123, \"array\":[1,2,3.4], \"map\":{\"m1\":\"v1\", \"m2\":\"v2\"}}"; + std::cout << "-- j3 -------------------\n" + << "input: " << input << "\n"; + JSON j3 (input); + j3.tree ()->dump (); + + // Sample ticket as a parsing test. + input = "{\n" + "\"ticket\": { \"type\":\"add\", \"client\":\"taskwarrior 2.x\"},\n" + "\"auth\": { \"user\":\"paul\", \"org\":\"gbf\", \"key\":\".........\",\n" + " \"locale\":\"en-US\" },\n" + "\n" + "\"add\": { \"description\":\"Wash the dog\",\n" + " \"project\":\"home\",\n" + " \"due\":\"20101101T000000Z\" }\n" + "}"; + std::cout << "-- j4 -------------------\n" + << "input: " << input << "\n"; + JSON j4 (input); + j4.tree ()->dump (); + std::cout << "-------------------------\n"; + + // Regular unit tests. + t.is (JSON::encode ("1\b2"), "1\\b2", "JSON::encode \\b -> \\\\b"); + t.is (JSON::decode ("1\\b2"), "1\b2", "JSON::decode \\\\b -> \\b"); + + t.is (JSON::encode ("1\n2"), "1\\n2", "JSON::encode \\n -> \\\\n"); + t.is (JSON::decode ("1\\n2"), "1\n2", "JSON::decode \\\\n -> \\n"); + + t.is (JSON::encode ("1\r2"), "1\\r2", "JSON::encode \\r -> \\\\r"); + t.is (JSON::decode ("1\\r2"), "1\r2", "JSON::decode \\\\r -> \\r"); + + t.is (JSON::encode ("1\t2"), "1\\t2", "JSON::encode \\t -> \\\\t"); + t.is (JSON::decode ("1\\t2"), "1\t2", "JSON::decode \\\\t -> \\t"); + + t.is (JSON::encode ("1\\2"), "1\\\\2", "JSON::encode \\ -> \\\\"); + t.is (JSON::decode ("1\\\\2"), "1\\2", "JSON::decode \\\\ -> \\"); + + t.is (JSON::encode ("1\x2"), "1\x2", "JSON::encode \\x -> \\x (NOP)"); + t.is (JSON::decode ("1\x2"), "1\x2", "JSON::decode \\x -> \\x (NOP)"); + + t.is (JSON::encode ("1€2"), "1€2", "JSON::encode € -> €"); + t.is (JSON::decode ("1\\u20ac2"), "1€2", "JSON::decode \\u20ac -> €"); + +/* + { + "ticket": + { + "type":"synch", + "client":"taskd-test-suite 1.0" + }, + + "synch": + { + "user": + { + "data": + [ + { + "uuid":"11111111-1111-1111-1111-111111111111", + "status":"pending", + "description":"This is a test", + "entry":"20110111T124000Z" + } + ], + "synch":"key" + } + }, + + "auth": + { + "org":"gbf", + "user":"Paul Beckingham", + "key":"K", + "locale":"en-US" + } + } +*/ + input = "{\"ticket\":{\"type\":\"synch\",\"client\":\"taskd-test-suite 1.0\"},\"synch\":{\"user\":{\"data\":[{\"uuid\":\"11111111-1111-1111-1111-111111111111\",\"status\":\"pending\",\"description\":\"This is a test\",\"entry\":\"20110111T124000Z\"}],\"synch\":\"key\"}},\"auth\":{\"org\":\"gbf\",\"user\":\"Paul Beckingham\",\"key\":\"K\",\"locale\":\"en-US\"}}"; + std::cout << "-- j4 -------------------\n" + << "input: " << input << "\n"; + JSON j5 (input); + j5.tree ()->dump (); + } + + catch (std::string& e) {t.diag (e);} + + return 0; +} + +//////////////////////////////////////////////////////////////////////////////// diff --git a/test/nibbler.t.cpp b/test/nibbler.t.cpp index 1b29e3b94..85d5c2b83 100644 --- a/test/nibbler.t.cpp +++ b/test/nibbler.t.cpp @@ -244,7 +244,7 @@ int main (int argc, char** argv) t.diag ("Nibbler::getNumber"); n = Nibbler ("-1.234 2.3e4"); t.ok (n.getNumber (d), "'-1.234 2.3e4' : getNumber () -> true"); - t.is (d, -1.234, "'-1.234 2.3e4' : getNumber () -> '-1.234'"); + t.is (d, -1.234, 0.000001, "'-1.234 2.3e4' : getNumber () -> '-1.234'"); t.ok (n.skip (' '), " ' 2.3e4' : skip (' ') -> true"); t.ok (n.getNumber (d), " '2.3e4' : getNumber () -> true"); t.is (d, 2.3e4, " '2.3e4' : getNumber () -> '2.3e4'");