functions.c File Reference

Functions for parsing files. Core of the library. More...

#include "functions.h"
#include <ctype.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <Python.h>
#include <string.h>
#include "classes/FastaBuff.h"
#include "classes/GtfDict.h"
#include "classes/GtfList.h"
#include "common.h"
#include "formats/fasta.h"
#include "formats/gtf.h"
#include "pyport.h"

Include dependency graph for functions.c:

Data Structures
struct	input_t
	Struct for storing input data for parsing functions. More...

Macros
#define	input_t_is_NULL(input)   (input.str == NULL)
	Checks if the input_t object is NULL.
#define	NULL_input_t    (input_t) { NULL, 0, NULL }
	NULL input_t object.

Functions
static void	free_input_t (input_t input)
	Frees the input_t object.
static input_t	getFileContentsFromArgs (PyObject *restrict first)
	Gets file contents object for parsing from python function arguments.
static int	addFasta (PyObject *list, const char *restrict title, size_t titleLen, PyObject *seq)
	Adds an entry to the FASTA tuple.
static void	echoProgress (PyObject *restrict echo, unsigned int lineIndex, unsigned int total)
	Echoes progress to a file.
static bool	processTextData (const char *restrict chunk, Py_ssize_t chunk_size, PyObject **out)
	Processes a chunk of FASTA text data.
static bool	processBinaryData (const char *restrict chunk, Py_ssize_t chunk_size, PyObject **out)
	Processes a chunk of binary FASTA data.
PyObject *	parseFasta (PyObject *self, PyObject *args, PyObject *restrict kwargs)
	Python function that parses provided raw FASTA content.
PyObject *	parseGTF (PyObject *restrict self, PyObject *restrict args, PyObject *restrict kwargs)
	Python function for parsing raw GTF file contents.

Detailed Description

Functions for parsing files. Core of the library.

Macro Definition Documentation

input_t_is_NULL

#define input_t_is_NULL

(

input

)

(input.str == NULL)

Checks if the input_t object is NULL.

Parameters

input

the input_t object to check

Returns

true or false depending on if the input_t object is NULL

NULL_input_t

#define NULL_input_t    (input_t) { NULL, 0, NULL }

NULL input_t object.

Returns

an input_t object with all fields set to NULL

Function Documentation

addFasta()

static int addFasta ( PyObject *  list, const char *restrict  title, size_t  titleLen, PyObject *  seq  )

inlinestatic

Adds an entry to the FASTA tuple.

Parameters

list	the list to add the entry to
title	the title of the entry
titleLen	the length of the title
seq	the sequence of the entry

Returns

the result of PyList_Append

See also

FastaBuff

Here is the caller graph for this function:

echoProgress()

static void echoProgress ( PyObject *restrict  echo, unsigned int  lineIndex, unsigned int  total  )

inlinestatic

Echoes progress to a file.

Echoes the progress of lineIndex/total to the file

Parameters

echo	the file to echo to
lineIndex	the current line index
total	the total amount of lines

Here is the caller graph for this function:

free_input_t()

static void free_input_t ( input_t  input )

static

Frees the input_t object.

Parameters

input

the input_t object to free

Warning

MUST BE CALLED WITH input_t_is_NULL(input) == false

Note

on *nix systems munmap() is used to free the memory mapped file

Here is the caller graph for this function:

getFileContentsFromArgs()

static input_t getFileContentsFromArgs ( PyObject *restrict  first )

static

Gets file contents object for parsing from python function arguments.

For performance reasons this function will attempt to get the file size using seek() and tell() if the object has those methods and then load the entire file using mmap(). If the object doesn't have seek() then it will just call read(-1).

Parameters

first

the first argument

Returns

a input_t object containing the file contents

Note

first needs to be either a string or have a read method

Here is the caller graph for this function:

processBinaryData()

static bool processBinaryData ( const char *restrict  chunk, Py_ssize_t  chunk_size, PyObject **  out  )

static

Processes a chunk of binary FASTA data.

Parameters

chunk	the chunk of data to process
chunk_size	the size of the chunk
out	the output buffer

Returns

true if ok, false if error

Here is the call graph for this function:

Here is the caller graph for this function:

processTextData()

static bool processTextData ( const char *restrict  chunk, Py_ssize_t  chunk_size, PyObject **  out  )

static

Processes a chunk of FASTA text data.

Parameters

chunk	the chunk of data to process
chunk_size	the size of the chunk
out	the output object, may be NULL

Returns

true if ok, false if error

Here is the caller graph for this function: