Glassvision/IfcOpenShell
1
0
Fork 0
mirror of https://github.com/IfcOpenShell/IfcOpenShell.git synced 2026-09-10 14:07:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

Performance improvement of IfcParse tokenizer (#82)

Browse Source 
* Applied MSVC tabify to IfcParse.cpp/h.

* Now Argument base class has throwing implementation for each conversion operator (removed those from derived classes).

* Added NullArgument class for the case when null arguments appear after setting elements.

* Now operator tokens are handled just like any other token.

* Refactoring: Token is now a struct with good fields, not a nameless pair.

* Now end position of token is set at its construction.

* Now type of token is determined on construction, as* function simply check stored type.

* Now int-s, float-s and some etc are parsed when token is created.

* Implemented simple way to remove spaces in parsing.

* Tokens are now created without allocations.

* Call RemoveTokenSeparators once for every token.

* Added temporary std::string object in lexer (for optimization purposes).

* Reimplemented asString without allocations.

* Parsing keywords without allocations.

* Added checks for type to tokenFunc::as*** functions.
This commit is contained in:
stgatilov
2016-06-09 22:25:50 +06:00
committed by Thomas Krijnen
parent cbbdb61a0c
commit 8725c66306
4 changed files with 246 additions and 181 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ifcparse/IfcParse.h
+55 -38
View File
@@ -60,7 +60,34 @@ namespace IfcParse {
class IfcFile;
class IfcSpfLexer;
typedef std::pair<IfcSpfLexer*, unsigned> Token;
enum TokenType {
Token_NONE,
Token_STRING,
Token_IDENTIFIER,
Token_OPERATOR,
Token_ENUMERATION,
Token_KEYWORD,
Token_INT,
Token_BOOL,
Token_FLOAT,
Token_BINARY
};
struct Token {
IfcSpfLexer* lexer; //TODO: remove it from here
unsigned startPos, endPos;
TokenType type;
union {
bool value_bool; //types: BOOL
char value_char; //types: OPERATOR
int value_int; //types: INT, IDENTIFIER
double value_double; //types: FLOAT
};
Token() : lexer(0), startPos(0), endPos(0), type(Token_NONE) {}
Token(IfcSpfLexer* _lexer, unsigned _startPos, unsigned _endPos, TokenType _type)
: lexer(_lexer), startPos(_startPos), endPos(_endPos), type(_type) {}
};
/// Provides functions to convert Tokens to binary data
/// Tokens are merely offsets to where they can be read in the file
@@ -75,7 +102,9 @@ namespace IfcParse {
/// Returns whether the token can be interpreted as an identifier
static bool isIdentifier(const Token& t);
/// Returns whether the token can be interpreted as a syntactical operator
static bool isOperator(const Token& t, char op = 0);
static bool isOperator(const Token& t);
/// Returns whether the token is a given operator
static bool isOperator(const Token& t, char op);
/// Returns whether the token can be interpreted as an enumerated value
static bool isEnumeration(const Token& t);
/// Returns whether the token can be interpreted as a datatype name
@@ -90,12 +119,16 @@ namespace IfcParse {
static bool isBinary(const Token& t);
/// Returns the token interpreted as an integer
static int asInt(const Token& t);
/// Returns the token interpreted as an identifier
static int asIdentifier(const Token& t);
/// Returns the token interpreted as an boolean (.T. or .F.)
static bool asBool(const Token& t);
/// Returns the token as a floating point number
static double asFloat(const Token& t);
/// Returns the token as a string (without the dot or apostrophe)
static std::string asString(const Token& t);
/// Returns the token as a string in internal buffer (for optimization purposes)
static const std::string &asStringRef(const Token& t);
/// Returns the token as a string (without the dot or apostrophe)
static boost::dynamic_bitset<> asBinary(const Token& t);
/// Returns a string representation of the token (including the dot or apostrophe)
@@ -106,23 +139,26 @@ namespace IfcParse {
// Functions for creating Tokens from an arbitary file offset
// The first 4 bits are reserved for Tokens of type ()=,;$*
//
Token TokenPtr(IfcSpfLexer* tokens, unsigned int offset);
Token TokenPtr(char c);
Token TokenPtr();
Token OperatorTokenPtr(IfcSpfLexer* tokens, unsigned start, unsigned end);
Token GeneralTokenPtr(IfcSpfLexer* tokens, unsigned start, unsigned end);
Token NoneTokenPtr();
/// A stream of tokens to be read from a IfcSpfStream.
class IfcParse_EXPORT IfcSpfLexer {
private:
IfcCharacterDecoder* decoder;
//storage for temporary string without allocation
mutable std::string _tempString;
unsigned int skipWhitespace();
unsigned int skipComment();
public:
std::string &GetTempString() const { return _tempString; }
IfcSpfStream* stream;
IfcFile* file;
IfcSpfLexer(IfcSpfStream* s, IfcFile* f);
Token Next();
~IfcSpfLexer();
std::string TokenString(unsigned int offset);
void TokenString(unsigned int offset, std::string &result);
};
/// Argument of type list, e.g.
@@ -139,13 +175,6 @@ namespace IfcParse {
IfcUtil::ArgumentType type() const;
operator int() const;
operator bool() const;
operator double() const;
operator std::string() const;
operator boost::dynamic_bitset<>() const;
operator IfcUtil::IfcBaseClass*() const;
operator std::vector<int>() const;
operator std::vector<double>() const;
operator std::vector<std::string>() const;
@@ -165,6 +194,19 @@ namespace IfcParse {
std::string toString(bool upper=false) const;
};
/// Argument being null, e.g. '$'
/// == ===
class IfcParse_EXPORT NullArgument : public Argument {
public:
NullArgument() {}
IfcUtil::ArgumentType type() const { return IfcUtil::Argument_NULL; }
bool isNull() const { return true; }
unsigned int size() const { return 1; }
Argument* operator [] (unsigned int /*i*/) const { throw IfcException("Argument is not a list of attributes"); }
std::string toString(bool /*upper=false*/) const { return "$"; }
};
/// Argument of type scalar or string, e.g.
/// #1=IfcVector(#2,1.0);
/// == ===
@@ -184,16 +226,6 @@ namespace IfcParse {
operator boost::dynamic_bitset<>() const;
operator IfcUtil::IfcBaseClass*() const;
operator std::vector<int>() const;
operator std::vector<double>() const;
operator std::vector<std::string>() const;
operator std::vector<boost::dynamic_bitset<> >() const;
operator IfcEntityList::ptr() const;
operator std::vector< std::vector<int> >() const;
operator std::vector< std::vector<double> >() const;
operator IfcEntityListList::ptr() const;
bool isNull() const;
unsigned int size() const;
@@ -213,23 +245,8 @@ namespace IfcParse {
IfcUtil::ArgumentType type() const;
operator int() const;
operator bool() const;
operator double() const;
operator std::string() const;
operator boost::dynamic_bitset<>() const;
operator IfcUtil::IfcBaseClass*() const;
operator std::vector<int>() const;
operator std::vector<double>() const;
operator std::vector<std::string>() const;
operator std::vector<boost::dynamic_bitset<> >() const;
operator IfcEntityList::ptr() const;
operator std::vector< std::vector<int> >() const;
operator std::vector< std::vector<double> >() const;
operator IfcEntityListList::ptr() const;
bool isNull() const;
unsigned int size() const;