From f76d1cde0a33131bf187d00385b8cfde7f45bbc6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=B6rg=20Frings-F=C3=BCrst?= Date: Fri, 8 Aug 2014 14:02:36 +0200 Subject: Initial import of fast-cpp-csv-parser version 0.0+git20140808~0a259084edad-1 --- csv.h | 1069 ++++++++++++++++++++++++++++++++++++++++ debian/README.source | 12 + debian/changelog | 5 + debian/compat | 1 + debian/control | 25 + debian/copyright | 54 ++ debian/doc-base | 13 + debian/doc/Documentation.html | 89 ++++ debian/doc/Documentation.pdf | Bin 0 -> 37896 bytes debian/doc/convert.sh | 3 + debian/docs | 2 + debian/install | 1 + debian/rules | 21 + debian/source/format | 1 + debian/source/include-binaries | 1 + debian/source/options | 2 + 16 files changed, 1299 insertions(+) create mode 100644 csv.h create mode 100644 debian/README.source create mode 100644 debian/changelog create mode 100644 debian/compat create mode 100644 debian/control create mode 100644 debian/copyright create mode 100644 debian/doc-base create mode 100644 debian/doc/Documentation.html create mode 100644 debian/doc/Documentation.pdf create mode 100755 debian/doc/convert.sh create mode 100644 debian/docs create mode 100644 debian/install create mode 100755 debian/rules create mode 100644 debian/source/format create mode 100644 debian/source/include-binaries create mode 100644 debian/source/options diff --git a/csv.h b/csv.h new file mode 100644 index 0000000..4ff5a53 --- /dev/null +++ b/csv.h @@ -0,0 +1,1069 @@ +// Copyright: (2012-2014) Ben Strasser +// License: BSD-3 +// +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are met: +// +// 1. Redistributions of source code must retain the above copyright notice, +// this list of conditions and the following disclaimer. +// +//2. Redistributions in binary form must reproduce the above copyright notice, +// this list of conditions and the following disclaimer in the documentation +// and/or other materials provided with the distribution. +// +//3. Neither the name of the copyright holder nor the names of its contributors +// may be used to endorse or promote products derived from this software +// without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +// ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE +// LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +// CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +// SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +// CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +// ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +// POSSIBILITY OF SUCH DAMAGE. + +#ifndef CSV_H +#define CSV_H + +#include +#include +#include +#include +#include +#include +#include +#ifndef CSV_IO_NO_THREAD +#include +#endif +#include +#include + +namespace io{ + //////////////////////////////////////////////////////////////////////////// + // LineReader // + //////////////////////////////////////////////////////////////////////////// + + namespace error{ + struct base : std::exception{ + virtual void format_error_message()const = 0; + + const char*what()const throw(){ + format_error_message(); + return error_message_buffer; + } + + mutable char error_message_buffer[256]; + }; + + const int max_file_name_length = 255; + + struct with_file_name{ + with_file_name(){ + std::memset(file_name, 0, max_file_name_length+1); + } + + void set_file_name(const char*file_name){ + std::strncpy(this->file_name, file_name, max_file_name_length); + this->file_name[max_file_name_length] = '\0'; + } + + char file_name[max_file_name_length+1]; + }; + + struct with_file_line{ + with_file_line(){ + file_line = -1; + } + + void set_file_line(int file_line){ + this->file_line = file_line; + } + + int file_line; + }; + + struct with_errno{ + with_errno(){ + errno = 0; + } + + void set_errno(int errno_value){ + this->errno_value = errno_value; + } + + int errno_value; + }; + + struct can_not_open_file : + base, + with_file_name, + with_errno{ + void format_error_message()const{ + if(errno_value != 0) + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Can not open file \"%s\" because \"%s\"." + , file_name, std::strerror(errno_value)); + else + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Can not open file \"%s\"." + , file_name); + } + }; + + struct line_length_limit_exceeded : + base, + with_file_name, + with_file_line{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Line number %d in file \"%s\" exceeds the maximum length of 2^24-1." + , file_line, file_name); + } + }; + } + + class LineReader{ + private: + static const int block_len = 1<<24; + #ifndef CSV_IO_NO_THREAD + std::futurebytes_read; + #endif + FILE*file; + char*buffer; + int data_begin; + int data_end; + + char file_name[error::max_file_name_length+1]; + unsigned file_line; + + void open_file(const char*file_name){ + // We open the file in binary mode as it makes no difference under *nix + // and under Windows we handle \r\n newlines ourself. + file = std::fopen(file_name, "rb"); + if(file == 0){ + int x = errno; // store errno as soon as possible, doing it after constructor call can fail. + error::can_not_open_file err; + err.set_errno(x); + err.set_file_name(file_name); + throw err; + } + } + + void init(){ + file_line = 0; + + // Tell the std library that we want to do the buffering ourself. + std::setvbuf(file, 0, _IONBF, 0); + + try{ + buffer = new char[3*block_len]; + }catch(...){ + std::fclose(file); + throw; + } + + data_begin = 0; + data_end = std::fread(buffer, 1, 2*block_len, file); + + // Ignore UTF-8 BOM + if(data_end >= 3 && buffer[0] == '\xEF' && buffer[1] == '\xBB' && buffer[2] == '\xBF') + data_begin = 3; + + #ifndef CSV_IO_NO_THREAD + if(data_end == 2*block_len){ + bytes_read = std::async(std::launch::async, [=]()->int{ + return std::fread(buffer + 2*block_len, 1, block_len, file); + }); + } + #endif + } + + public: + LineReader() = delete; + LineReader(const LineReader&) = delete; + LineReader&operator=(const LineReader&) = delete; + + LineReader(const char*file_name, FILE*file): + file(file){ + set_file_name(file_name); + init(); + } + + LineReader(const std::string&file_name, FILE*file): + file(file){ + set_file_name(file_name.c_str()); + init(); + } + + explicit LineReader(const char*file_name){ + set_file_name(file_name); + open_file(file_name); + init(); + } + + explicit LineReader(const std::string&file_name){ + set_file_name(file_name.c_str()); + open_file(file_name.c_str()); + init(); + } + + void set_file_name(const std::string&file_name){ + set_file_name(file_name.c_str()); + } + + void set_file_name(const char*file_name){ + strncpy(this->file_name, file_name, error::max_file_name_length); + this->file_name[error::max_file_name_length] = '\0'; + } + + const char*get_truncated_file_name()const{ + return file_name; + } + + void set_file_line(unsigned file_line){ + this->file_line = file_line; + } + + unsigned get_file_line()const{ + return file_line; + } + + char*next_line(){ + if(data_begin == data_end) + return 0; + + ++file_line; + + assert(data_begin < data_end); + assert(data_end <= block_len*2); + + if(data_begin >= block_len){ + std::memcpy(buffer, buffer+block_len, block_len); + data_begin -= block_len; + data_end -= block_len; + #ifndef CSV_IO_NO_THREAD + if(bytes_read.valid()) + #endif + { + #ifndef CSV_IO_NO_THREAD + data_end += bytes_read.get(); + #else + data_end += std::fread(buffer + 2*block_len, 1, block_len, file); + #endif + std::memcpy(buffer+block_len, buffer+2*block_len, block_len); + + #ifndef CSV_IO_NO_THREAD + bytes_read = std::async(std::launch::async, [=]()->int{ + return std::fread(buffer + 2*block_len, 1, block_len, file); + }); + #endif + } + } + + int line_end = data_begin; + while(buffer[line_end] != '\n' && line_end != data_end){ + ++line_end; + } + + if(line_end - data_begin + 1 > block_len){ + error::line_length_limit_exceeded err; + err.set_file_name(file_name); + err.set_file_line(file_line); + throw err; + } + + if(buffer[line_end] == '\n'){ + buffer[line_end] = '\0'; + }else{ + // some files are missing the newline at the end of the + // last line + ++data_end; + buffer[line_end] = '\0'; + } + + // handle windows \r\n-line breaks + if(line_end != data_begin && buffer[line_end-1] == '\r') + buffer[line_end-1] = '\0'; + + char*ret = buffer + data_begin; + data_begin = line_end+1; + return ret; + } + + ~LineReader(){ + #ifndef CSV_IO_NO_THREAD + // GCC needs this or it will crash. + if(bytes_read.valid()) + bytes_read.get(); + #endif + + delete[] buffer; + std::fclose(file); + } + }; + + //////////////////////////////////////////////////////////////////////////// + // CSV // + //////////////////////////////////////////////////////////////////////////// + + namespace error{ + const int max_column_name_length = 63; + struct with_column_name{ + with_column_name(){ + std::memset(column_name, 0, max_column_name_length+1); + } + + void set_column_name(const char*column_name){ + std::strncpy(this->column_name, column_name, max_column_name_length); + this->column_name[max_column_name_length] = '\0'; + } + + char column_name[max_column_name_length+1]; + }; + + + const int max_column_content_length = 63; + + struct with_column_content{ + with_column_content(){ + std::memset(column_content, 0, max_column_content_length+1); + } + + void set_column_content(const char*column_content){ + std::strncpy(this->column_content, column_content, max_column_content_length); + this->column_content[max_column_content_length] = '\0'; + } + + char column_content[max_column_content_length+1]; + }; + + + struct extra_column_in_header : + base, + with_file_name, + with_column_name{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Extra column \"%s\" in header of file \"%s\"." + , column_name, file_name); + } + }; + + struct missing_column_in_header : + base, + with_file_name, + with_column_name{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Missing column \"%s\" in header of file \"%s\"." + , column_name, file_name); + } + }; + + struct duplicated_column_in_header : + base, + with_file_name, + with_column_name{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Duplicated column \"%s\" in header of file \"%s\"." + , column_name, file_name); + } + }; + + struct header_missing : + base, + with_file_name{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Header missing in file \"%s\"." + , file_name); + } + }; + + struct too_few_columns : + base, + with_file_name, + with_file_line{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Too few columns in line %d in file \"%s\"." + , file_line, file_name); + } + }; + + struct too_many_columns : + base, + with_file_name, + with_file_line{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Too many columns in line %d in file \"%s\"." + , file_line, file_name); + } + }; + + struct escaped_string_not_closed : + base, + with_file_name, + with_file_line{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "Escaped string was not closed in line %d in file \"%s\"." + , file_line, file_name); + } + }; + + struct integer_must_be_positive : + base, + with_file_name, + with_file_line, + with_column_name, + with_column_content{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "The integer \"%s\" must be positive or 0 in column \"%s\" in file \"%s\" in line \"%d\"." + , column_content, column_name, file_name, file_line); + } + }; + + struct no_digit : + base, + with_file_name, + with_file_line, + with_column_name, + with_column_content{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "The integer \"%s\" contains an invalid digit in column \"%s\" in file \"%s\" in line \"%d\"." + , column_content, column_name, file_name, file_line); + } + }; + + struct integer_overflow : + base, + with_file_name, + with_file_line, + with_column_name, + with_column_content{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "The integer \"%s\" overflows in column \"%s\" in file \"%s\" in line \"%d\"." + , column_content, column_name, file_name, file_line); + } + }; + + struct integer_underflow : + base, + with_file_name, + with_file_line, + with_column_name, + with_column_content{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "The integer \"%s\" underflows in column \"%s\" in file \"%s\" in line \"%d\"." + , column_content, column_name, file_name, file_line); + } + }; + + struct invalid_single_character : + base, + with_file_name, + with_file_line, + with_column_name, + with_column_content{ + void format_error_message()const{ + std::snprintf(error_message_buffer, sizeof(error_message_buffer), + "The content \"%s\" of column \"%s\" in file \"%s\" in line \"%d\" is not a single character." + , column_content, column_name, file_name, file_line); + } + }; + } + + typedef unsigned ignore_column; + static const ignore_column ignore_no_column = 0; + static const ignore_column ignore_extra_column = 1; + static const ignore_column ignore_missing_column = 2; + + template + struct trim_chars{ + private: + constexpr static bool is_trim_char(char c){ + return false; + } + + template + constexpr static bool is_trim_char(char c, char trim_char, OtherTrimChars...other_trim_chars){ + return c == trim_char || is_trim_char(c, other_trim_chars...); + } + + public: + static void trim(char*&str_begin, char*&str_end){ + while(is_trim_char(*str_begin, trim_char_list...) && str_begin != str_end) + ++str_begin; + while(is_trim_char(*(str_end-1), trim_char_list...) && str_begin != str_end) + --str_end; + *str_end = '\0'; + } + }; + + + struct no_comment{ + static bool is_comment(const char*line){ + return false; + } + }; + + template + struct single_line_comment{ + private: + constexpr static bool is_comment_start_char(char c){ + return false; + } + + template + constexpr static bool is_comment_start_char(char c, char comment_start_char, OtherCommentStartChars...other_comment_start_chars){ + return c == comment_start_char || is_comment_start_char(c, other_comment_start_chars...); + } + + public: + + static bool is_comment(const char*line){ + return is_comment_start_char(*line, comment_start_char_list...); + } + }; + + struct empty_line_comment{ + static bool is_comment(const char*line){ + if(*line == '\0') + return true; + while(*line == ' ' || *line == '\t'){ + ++line; + if(*line == 0) + return true; + } + return false; + } + }; + + template + struct single_and_empty_line_comment{ + static bool is_comment(const char*line){ + return single_line_comment::is_comment(line) || empty_line_comment::is_comment(line); + } + }; + + template + struct no_quote_escape{ + static const char*find_next_column_end(const char*col_begin){ + while(*col_begin != sep && *col_begin != '\0') + ++col_begin; + return col_begin; + } + + static void unescape(char*&col_begin, char*&col_end){ + + } + }; + + template + struct double_quote_escape{ + static const char*find_next_column_end(const char*col_begin){ + while(*col_begin != sep && *col_begin != '\0') + if(*col_begin != quote) + ++col_begin; + else{ + do{ + ++col_begin; + while(*col_begin != quote){ + if(*col_begin == '\0') + throw error::escaped_string_not_closed(); + ++col_begin; + } + ++col_begin; + }while(*col_begin == quote); + } + return col_begin; + } + + static void unescape(char*&col_begin, char*&col_end){ + if(col_end - col_begin >= 2){ + if(*col_begin == quote && *(col_end-1) == quote){ + ++col_begin; + --col_end; + char*out = col_begin; + for(char*in = col_begin; in!=col_end; ++in){ + if(*in == quote && *(in+1) == quote){ + continue; + } + *out = *in; + ++out; + } + col_end = out; + *col_end = '\0'; + } + } + + } + }; + + struct throw_on_overflow{ + template + static void on_overflow(T&){ + throw error::integer_overflow(); + } + + template + static void on_underflow(T&){ + throw error::integer_underflow(); + } + }; + + struct ignore_overflow{ + template + static void on_overflow(T&){} + + template + static void on_underflow(T&){} + }; + + struct set_to_max_on_overflow{ + template + static void on_overflow(T&x){ + x = std::numeric_limits::max(); + } + + template + static void on_underflow(T&x){ + x = std::numeric_limits::min(); + } + }; + + + namespace detail{ + template + void chop_next_column( + char*&line, char*&col_begin, char*&col_end + ){ + assert(line != nullptr); + + col_begin = line; + // the col_begin + (... - col_begin) removes the constness + col_end = col_begin + (quote_policy::find_next_column_end(col_begin) - col_begin); + + if(*col_end == '\0'){ + line = nullptr; + }else{ + *col_end = '\0'; + line = col_end + 1; + } + } + + template + void parse_line( + char*line, + char**sorted_col, + const std::vector&col_order + ){ + for(std::size_t i=0; i(line, col_begin, col_end); + + if(col_order[i] != -1){ + trim_policy::trim(col_begin, col_end); + quote_policy::unescape(col_begin, col_end); + + sorted_col[col_order[i]] = col_begin; + } + } + if(line != nullptr) + throw io::error::too_many_columns(); + } + + template + void parse_header_line( + char*line, + std::vector&col_order, + const std::string*col_name, + ignore_column ignore_policy + ){ + col_order.clear(); + + bool found[column_count]; + std::fill(found, found + column_count, false); + while(line){ + char*col_begin,*col_end; + chop_next_column(line, col_begin, col_end); + + trim_policy::trim(col_begin, col_end); + quote_policy::unescape(col_begin, col_end); + + for(unsigned i=0; i + void parse(char*col, char &x){ + if(!*col) + throw error::invalid_single_character(); + x = *col; + ++col; + if(*col) + throw error::invalid_single_character(); + } + + template + void parse(char*col, std::string&x){ + x = col; + } + + template + void parse(char*col, const char*&x){ + x = col; + } + + template + void parse(char*col, char*&x){ + x = col; + } + + template + void parse_unsigned_integer(const char*col, T&x){ + x = 0; + while(*col != '\0'){ + if('0' <= *col && *col <= '9'){ + T y = *col - '0'; + if(x > (std::numeric_limits::max()-y)/10){ + overflow_policy::on_overflow(x); + return; + } + x = 10*x+y; + }else + throw error::no_digit(); + ++col; + } + } + + templatevoid parse(char*col, unsigned char &x) + {parse_unsigned_integer(col, x);} + templatevoid parse(char*col, unsigned short &x) + {parse_unsigned_integer(col, x);} + templatevoid parse(char*col, unsigned int &x) + {parse_unsigned_integer(col, x);} + templatevoid parse(char*col, unsigned long &x) + {parse_unsigned_integer(col, x);} + templatevoid parse(char*col, unsigned long long &x) + {parse_unsigned_integer(col, x);} + + template + void parse_signed_integer(const char*col, T&x){ + if(*col == '-'){ + ++col; + + x = 0; + while(*col != '\0'){ + if('0' <= *col && *col <= '9'){ + T y = *col - '0'; + if(x < (std::numeric_limits::min()+y)/10){ + overflow_policy::on_underflow(x); + return; + } + x = 10*x-y; + }else + throw error::no_digit(); + ++col; + } + return; + }else if(*col == '+') + ++col; + parse_unsigned_integer(col, x); + } + + templatevoid parse(char*col, signed char &x) + {parse_signed_integer(col, x);} + templatevoid parse(char*col, signed short &x) + {parse_signed_integer(col, x);} + templatevoid parse(char*col, signed int &x) + {parse_signed_integer(col, x);} + templatevoid parse(char*col, signed long &x) + {parse_signed_integer(col, x);} + templatevoid parse(char*col, signed long long &x) + {parse_signed_integer(col, x);} + + template + void parse_float(const char*col, T&x){ + bool is_neg = false; + if(*col == '-'){ + is_neg = true; + ++col; + }else if(*col == '+') + ++col; + + x = 0; + while('0' <= *col && *col <= '9'){ + int y = *col - '0'; + x *= 10; + x += y; + ++col; + } + + if(*col == '.'|| *col == ','){ + ++col; + T pos = 1; + while('0' <= *col && *col <= '9'){ + pos /= 10; + int y = *col - '0'; + ++col; + x += y*pos; + } + } + + if(*col == 'e' || *col == 'E'){ + ++col; + int e; + + parse_signed_integer(col, e); + + if(e != 0){ + T base; + if(e < 0){ + base = 0.1; + e = -e; + }else{ + base = 10; + } + + while(e != 1){ + if((e & 1) == 0){ + base = base*base; + e >>= 1; + }else{ + x *= base; + --e; + } + } + x *= base; + } + }else{ + if(*col != '\0') + throw error::no_digit(); + } + + if(is_neg) + x = -x; + } + + template void parse(char*col, float&x) { parse_float(col, x); } + template void parse(char*col, double&x) { parse_float(col, x); } + template void parse(char*col, long double&x) { parse_float(col, x); } + + template + void parse(char*col, T&x){ + // GCC evalutes "false" when reading the template and + // "sizeof(T)!=sizeof(T)" only when instantiating it. This is why + // this strange construct is used. + static_assert(sizeof(T)!=sizeof(T), + "Can not parse this type. Only buildin integrals, floats, char, char*, const char* and std::string are supported"); + } + + } + + template, + class quote_policy = no_quote_escape<','>, + class overflow_policy = throw_on_overflow, + class comment_policy = no_comment + > + class CSVReader{ + private: + LineReader in; + + char*(row[column_count]); + std::string column_names[column_count]; + + std::vectorcol_order; + + template + void set_column_names(std::string s, ColNames...cols){ + column_names[column_count-sizeof...(ColNames)-1] = std::move(s); + set_column_names(std::forward(cols)...); + } + + void set_column_names(){} + + + public: + CSVReader() = delete; + CSVReader(const CSVReader&) = delete; + CSVReader&operator=(const CSVReader&); + + template + explicit CSVReader(Args...args):in(std::forward(args)...){ + std::fill(row, row+column_count, nullptr); + col_order.resize(column_count); + for(unsigned i=0; i + void read_header(ignore_column ignore_policy, ColNames...cols){ + static_assert(sizeof...(ColNames)>=column_count, "not enough column names specified"); + static_assert(sizeof...(ColNames)<=column_count, "too many column names specified"); + try{ + set_column_names(std::forward(cols)...); + + char*line; + do{ + line = in.next_line(); + if(!line) + throw error::header_missing(); + }while(comment_policy::is_comment(line)); + + detail::parse_header_line + + (line, col_order, column_names, ignore_policy); + }catch(error::with_file_name&err){ + err.set_file_name(in.get_truncated_file_name()); + throw; + } + } + + template + void set_header(ColNames...cols){ + static_assert(sizeof...(ColNames)>=column_count, + "not enough column names specified"); + static_assert(sizeof...(ColNames)<=column_count, + "too many column names specified"); + set_column_names(std::forward(cols)...); + std::fill(row, row+column_count, nullptr); + col_order.resize(column_count); + for(unsigned i=0; i + void parse_helper(std::size_t r, T&t, ColType&...cols){ + if(row[r]){ + try{ + try{ + row[r] = row[r]; + io::detail::parse(row[r], t); + }catch(error::with_column_content&err){ + err.set_column_content(row[r]); + throw; + } + }catch(error::with_column_name&err){ + err.set_column_name(column_names[r].c_str()); + throw; + } + } + parse_helper(r+1, cols...); + } + + + public: + template + bool read_row(ColType& ...cols){ + static_assert(sizeof...(ColType)>=column_count, + "not enough columns specified"); + static_assert(sizeof...(ColType)<=column_count, + "too many columns specified"); + try{ + try{ + + char*line; + do{ + line = in.next_line(); + if(!line) + return false; + }while(comment_policy::is_comment(line)); + + detail::parse_line + (line, row, col_order); + + parse_helper(0, cols...); + }catch(error::with_file_name&err){ + err.set_file_name(in.get_truncated_file_name()); + throw; + } + }catch(error::with_file_line&err){ + err.set_file_line(in.get_file_line()); + throw; + } + + return true; + } + }; +} +#endif + diff --git a/debian/README.source b/debian/README.source new file mode 100644 index 0000000..b840888 --- /dev/null +++ b/debian/README.source @@ -0,0 +1,12 @@ +fccp for Debian +--------------- + +This header-only library has no upstream tarball. +It was downloaded and packed via debian/rule get-orig-sources. + +The documentation is a modified site from the wiki, installed in debian/doc. +The pdf file was generated with "wkhtmltopdf Documentation.html Documentation.pdf". +The batch is also in debian/doc. + + -- Jörg Frings-Fürst Mon, 28 Apr 2014 11:10:13 +0200 + diff --git a/debian/changelog b/debian/changelog new file mode 100644 index 0000000..b335d1f --- /dev/null +++ b/debian/changelog @@ -0,0 +1,5 @@ +fast-cpp-csv-parser (0.0+git20140808~0a259084edad-1) unstable; urgency=low + + * Initial release (Closes: #745898) + + -- Jörg Frings-Fürst Fri, 08 Aug 2014 13:35:44 +0200 diff --git a/debian/compat b/debian/compat new file mode 100644 index 0000000..ec63514 --- /dev/null +++ b/debian/compat @@ -0,0 +1 @@ +9 diff --git a/debian/control b/debian/control new file mode 100644 index 0000000..7493780 --- /dev/null +++ b/debian/control @@ -0,0 +1,25 @@ +Source: fast-cpp-csv-parser +Section: devel +Priority: optional +Maintainer: Jörg Frings-Fürst +Build-Depends: + debhelper (>= 9) +Standards-Version: 3.9.5 +Homepage: https://code.google.com/p/fast-cpp-csv-parser/ + +Package: fast-cpp-csv-parser +Architecture: all +Depends: ${shlibs:Depends}, ${misc:Depends} +Description: Fast C++ CSV Parser + Automatically rearranges columns by parsing the header line. + Disk I/O and CSV-parsing are overlapped using threads for efficiency. + Parsing features such as escaped strings can be enabled and disabled + at compile time using templates. You only pay in speed for the + features you actually use. + Can read multiple GB files in reasonable time. + Support for custom columns separators (i.e. Tab separated value files + are supported), quote escaped strings, automatic space trimming. + Works with *nix and Windows newlines and automatically ignores UTF-8 BOMs. + Exception classes with enough context to format useful error messages. + what() returns error messages ready to be shown to a user. + diff --git a/debian/copyright b/debian/copyright new file mode 100644 index 0000000..8c9e49b --- /dev/null +++ b/debian/copyright @@ -0,0 +1,54 @@ +Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/ +Upstream-Name: fast-cpp-csv-parser +Source: https://code.google.com/p/fast-cpp-csv-parser/source/browse/csv.h + +Files: * +Copyright: 2012-2014 Ben Strasser +License: BSD-3-Clause + +Files: debian/* +Copyright: 2014 Jörg Frings-Fürst +License: GPL-3.0+ + +License: BSD-3-Clause + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + 2. Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + 3. Neither the name of the University nor the names of its contributors + may be used to endorse or promote products derived from this software + without specific prior written permission. + . + THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE HOLDERS OR + CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, + PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR + PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +License: GPL-3.0+ + 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 package 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, see . + . + On Debian systems, the complete text of the GNU General + Public License version 3 can be found in "/usr/share/common-licenses/GPL-3". + diff --git a/debian/doc-base b/debian/doc-base new file mode 100644 index 0000000..d80a26e --- /dev/null +++ b/debian/doc-base @@ -0,0 +1,13 @@ +Document: fast-cpp-csv-parser +Title: Debian fccp Manual +Author: Ben Strasser +Abstract: This manual describes what fast-cpp-csv-parser is + and how it can be used. +Section: Programming/C++ + +Format: PDF +Files: /usr/share/doc/fast-cpp-csv-parser/Documentation.pdf.gz + +Format: html +Index: /usr/share/doc/fast-cpp-csv-parser/Documentation.html +Files: /usr/share/doc/fast-cpp-csv-parser/*.html diff --git a/debian/doc/Documentation.html b/debian/doc/Documentation.html new file mode 100644 index 0000000..9c84a51 --- /dev/null +++ b/debian/doc/Documentation.html @@ -0,0 +1,89 @@ + + + + + + +Documentation - fast-cpp-csv-parser - Fast C++ CSV Parser + + + + +
+
+

Documentation - fast-cpp-csv-parser

+

The libary provides two classes:

  • LineReader: A class to efficiently read large files line by line.
  • CSVReader: A class that efficiently reads large CSV files.

Note that everything is contained in the io namespace.

LineReader

class LineReader{
+public:
+  // Constructors
+  LineReader(some_string_type file_name);
+  LineReader(some_string_type file_name, std::FILE*file);
+
+  // Reading
+  char*next_line();
+
+  // File Location
+  void set_file_line(unsigned);
+  unsigned get_file_line(unsigned)const;
+  void set_file_name(some_string_type file_name);
+  const char*get_truncated_file_name()const;
+};

The constructor takes a file name and optionally a stdio.h file handle. If no file handle is provided the class tries to open the file and throws an error::can_not_open_file exception on failure. If a file handle is provided then the file name is only used to format error messages. The library will call std::fclose on the file handle. some_string_type can be a std::string or a char*.

Lines are read by calling the next_line function. It returns a pointer to a null terminated C-string that contains the line. If the end of file is reached a null pointer is returned. The newline character is not included in the string. You may modify the string as long as you do not write past the null terminator. The string stays valid until the destructor is called or until next_line is called again. Windows and *nix newlines are handled transparently. UTF-8 BOMs are automatically ignored and missing newlines at the end of the file are no problem.

Important: There is a limit of 2^24-1 characters per line. If this limit is exceeded a error::line_length_limit_exceeded exception is thrown.

Looping over all the lines in a file can be done in the following way. 

LineReader in(...);
+while(char*line = in.next_line()){
+  ...
+}

The remaining functions are mainly used used to format error messages. The file line indicates the current position in the file, i.e., after the first next_line call it is 1 and after the second 2. Before the first call it is 0. The file name is truncated as internally C-strings are used to avoid std::bad_alloc exceptions during error reporting.

Note: It is not possible to exchange the line termination character.

CSVReader

CSVReader uses policies. These are classes with only static members to allow core functionality to be exchanged in an efficient way. 

template<
+  unsigned column_count,
+  class trim_policy = trim_chars<' ', '\t'>, 
+  class quote_policy = no_quote_escape<','>,
+  class overflow_policy = throw_on_overflow,
+  class comment_policy = no_comment
+>
+class CSVReader{
+public:
+  // Constructors
+  CSVReader(some_string_type file_name);
+  CSVReader(some_string_type file_name, std::FILE*file);
+
+  // Parsing Header
+  void read_header(ignore_column ignore_policy, some_string_type col_name1, some_string_type col_name2, ...);
+  void set_header(some_string_type col_name1, some_string_type col_name2, ...);
+  bool has_column(some_string_type col_name)const;
+
+  // Read
+  bool read_row(ColType1&col1, ColType2&col2, ...);
+
+  // File Location  
+  void set_file_line(unsigned);
+  unsigned get_file_line(unsigned)const;
+  void set_file_name(some_string_type file_name);
+  const char*get_truncated_file_name()const;
+};

The column_count template parameter indicates how many columns you want to read from the CSV file. This must not necessarily coincide with the actual number of columns in the file. The three policies govern various aspects of the parsing.

The trim policy indicates what characters should be ignored at the begin and the end of every column. The default ignores spaces and tabs. This makes sure that 

a,b,c
+1,2,3

is interpreted in the same way as 

  a, b,   c
+1  , 2,   3

The trim_chars can take any number of template parameters. For example trim_chars<' ', '\t', '_'> is also valid. If no character should be trimmed use trim_chars<>.

The quote policy indicates how string should be escaped. It also specifies the column separator. The predefined policies are:

  • no_quote_escape<sep> : Strings are not escaped. "sep" is used as column separator.
  • double_quote_escape<sep, quote> : Strings are escaped using quotes. Quotes are escaped using two consecutive quotes. "sep" is used as column separator and "quote" as quoting character.

Important: Quoting can be quite expensive. Disable it if you do not need it.

The overflow policy indicates what should be done if the integers in the input are too large to fit into the variables. There following policies are predefined:

  • throw_on_overflow : Throw an error::integer_overflow or error::integer_underflow exception.
  • ignore_overflow : Do nothing and let the overflow happen.
  • set_to_max_on_overflow : Set the value to numeric_limits<...>::max() (or to the min-pendant).

The comment policy allows to skip lines based on some criteria. Valid predefined policies are:

  • no_comment : Do not ignore any line.
  • empty_line_comment : Ignore all lines that are empty or only contains spaces and tabs.
  • single_line_comment<com1, com2, ...> : Ignore all lines that start with com1 or com2 or ... as the first character. There may not be any space between the beginning of the line and the comment character.
  • single_and_empty_line_comment<com1, com2, ...> : Ignore all empty lines and single line comments.

Examples:

  • CSVReader<4, trim_chars<' '>, double_quote_escape<',','\"'> > reads 4 columns from a normal CSV file with string escaping enabled.
  • CSVReader<3, trim_chars<' '>, no_quote_escape<'\t'>, single_line_comment<'#'> > reads 3 columns from a tab separated file with string escaping disabled. Lines starting with a # are ignored.

The constructors and the file location functions are exactly the same as for LineReader. See its documentation for details.

There are three methods that deal with headers. The read_header methods reads a line from the file and rearranges the columns to match that order. It also checks whether all necessary columns are present. The set_header method does not read any input. Use it if the file does not have any header. Obviously it is impossible to rearrange columns or check for their availability when using it. The order in the file and in the program must match when using set_header. The has_column method checks whether a column is present in the file. The first argument of read_header is a bitfield that determines how the function should react to column mismatches. The default behavior is to throw an error::extra_column_in_header exception if the file contains more columns than expected and an error::missing_column_in_header when there are not enough. This behavior can be altered using the following flags.

  • ignore_no_column: The default behavior, no flags are set
  • ignore_extra_column: If a column with a name is in the file but not in the argument list, then it is silently ignored.
  • ignore_missing_column: If a column with a name is not in the file but is in the argument list, then read_row will not modify the corresponding variable.

When using ignore_column_missing it is a good idea to initialize the variables passed to read_row with a default value, for example: 

// The file only contains column "a"
+CSVReader<2>in(...);
+in.read_header(ignore_missing_column, "a", "b");
+int a,b = 42;
+while(in.read_row(a,b)){
+  // a contains the value from the file
+  // b is left unchanged by read_row, i.e., it is 42
+}

If only some columns are optional or their default value depends on other columns you have to use has_column, for example: 

// The file only contains the columns "a" and "b"
+CSVReader<2>in(...);
+in.read_header(ignore_missing_column, "a", "b", "sum");
+if(!in.has_column("a") || !in.has_column("b"))
+  throw my_neat_error_class();
+bool has_sum = in.has_column("sum");
+int a,b,sum;
+while(in.read_row(a,b,sum)){
+  if(!has_sum)
+    sum = a+b;
+}

Important: Do not call has_column from within the read-loop. It would work correctly but significantly slowdown processing.

If two columns have the same name an error::duplicated_column_in_header exception is thrown. If read_header is called but the file is empty a error::header_missing exception is thrown.

The read_row function reads a line, splits it into the columns and arranges them correctly. It trims the entries and unescapes them. If requested the content is interpreted as integer or as floating point. The variables passed to read_row may be of the following types.

  • builtin signed integer: These are signed char, short, int, long and long long. The input must be encoded as a base 10 ASCII number optionally preceded by a + or -. The function detects whether the integer is too large would overflow (or underflow) and behaves as indicated by overflow_policy.
  • builtin unsigned integer: Just as the signed counterparts except that a leading + or - is not allowed.
  • builtin floating point: These are float, double and long double. The input may have a leading + or -. The number must be base 10 encoded. The decimal point may either be a dot or a comma. (Note that a comma will only work if it is not also used as column separator or the number is escaped.) A base 10 exponent may be specified using the "1e10" syntax. The "e" may be lower- or uppercase. Examples for valid floating points are "1", "-42.42" and "+123.456E789". The input is rounded to the next floating point or infinity if it is too large or small.
  • char: The column content must be a single character.
  • std::string: The column content is assigned to the string. The std::string is filled with the trimmed and unescaped version.
  • char*: A pointer directly into the buffer. The string is trimmed and unescaped and null terminated. This pointer stays valid until read_row is called again or the CSVReader is destroyed. Use this for user defined types.

Note that there is no inherent overhead to using char* and then interpreting it compared to using one of the parsers directly build into CSVReader. The builtin number parsers are pure convenience. If you need a slightly different syntax then use char* and do the parsing yourself.

+
+
+ + + + + + + + + + diff --git a/debian/doc/Documentation.pdf b/debian/doc/Documentation.pdf new file mode 100644 index 0000000..bb78956 Binary files /dev/null and b/debian/doc/Documentation.pdf differ diff --git a/debian/doc/convert.sh b/debian/doc/convert.sh new file mode 100755 index 0000000..f8544ed --- /dev/null +++ b/debian/doc/convert.sh @@ -0,0 +1,3 @@ +#!/bin/bash + +wkhtmltopdf Documentation.html Documentation.pdf diff --git a/debian/docs b/debian/docs new file mode 100644 index 0000000..4b24dc5 --- /dev/null +++ b/debian/docs @@ -0,0 +1,2 @@ +debian/doc/Documentation.html +debian/doc/Documentation.pdf diff --git a/debian/install b/debian/install new file mode 100644 index 0000000..17d779e --- /dev/null +++ b/debian/install @@ -0,0 +1 @@ +csv.h usr/include/fast_cpp_csv_parser/ diff --git a/debian/rules b/debian/rules new file mode 100755 index 0000000..ae186f8 --- /dev/null +++ b/debian/rules @@ -0,0 +1,21 @@ +#!/usr/bin/make -f + + +# Uncomment this to turn on verbose mode. +#export DH_VERBOSE=1 + + +PKD = $(abspath $(dir $(MAKEFILE_LIST))) +PKG = $(word 2,$(shell dpkg-parsechangelog -l$(PKD)/changelog | grep ^Source)) +VER = $(shell dpkg-parsechangelog -l$(PKD)/changelog -SVersion | cut -d- -f1) + + +%: + dh $@ + +override_dh_auto_build: + +get-orig-source: $(info I: $(PKG)_$(VER)) + cd ${CURDIR} + wget https://fast-cpp-csv-parser.googlecode.com/git/csv.h -O csv.h + tar -cJf ../$(PKG)_$(VER).orig.tar.xz *.h diff --git a/debian/source/format b/debian/source/format new file mode 100644 index 0000000..163aaf8 --- /dev/null +++ b/debian/source/format @@ -0,0 +1 @@ +3.0 (quilt) diff --git a/debian/source/include-binaries b/debian/source/include-binaries new file mode 100644 index 0000000..8fecf38 --- /dev/null +++ b/debian/source/include-binaries @@ -0,0 +1 @@ +debian/doc/Documentation.pdf diff --git a/debian/source/options b/debian/source/options new file mode 100644 index 0000000..22a4de9 --- /dev/null +++ b/debian/source/options @@ -0,0 +1,2 @@ +compression = xz +compression-level = 9 -- cgit v1.2.3