split

Bash: Extract data from files both filtering filename, the path and doing internal processing

 in Bash / GNU/Linux  tagged awk / bash / cut / find / grep / hashmap / match / sort / split / unique by

The following code will find all files that match the pattern 2016_*_*.log (all the log files for the year 2016).

To avoid finding log files from other services than the Web API service, we filter only the files that their path contains the folder webapi. Specifically, we used "/ServerLogs/*/webapi/*" with the following command to match all files that are under the folder /ServerLogs/ and somewhere in the path there is another folder named webapi, we do that to match files that are like /ServerLogs/Production/01/webapi/* only. The way we coded our regular expression, it will not match if there is a folder called webapi directly under the /ServerLogs/ (e.g. /ServerLogs/webapi/*).

For each result, we execute an awk script that will split the lines using the comma (FS=",";) character, then check if the line contains exactly 4 tokens (if (NF == 4) {). Later, we get the 4th token and check if it contains the substring "MASTER=" (if (match($4,"MASTER=")) {), if it does contain it we split it using the space character and assign the result to the variable named tokens. From tokens, we get the first token and use substr to remove the first character. Finally, we use the formatted result to create an array where the keys are the values we just created and it is used as a hashmap to keep record of all unique strings. In the end clause, we print all the elements of our hash map.

Finally, we sort all the results from all the awk executions and remove duplicates using sort --unique.


find /ServerLogs/ \
    -iname "2016_*_*.log" \
    -ipath "/ServerLogs/*/webapi/*" \
    -exec awk '
        BEGIN {
            FS=",";
        }
        {
            if (NF == 4) {
                if (match($4,"MASTER=")) {
                    split($4, tokens, " ");
                    instances[substr(tokens[1], 2)];
                }
            }
        }
        END {
            for (element in instances) {
                print element;
            }
        }
    ' \
    '{}' \; | sort --unique;

Following is the same code in one line.

 find /ServerLogs/ -iname "2016_*_*.log" -ipath "/ServerLogs/*/webapi/*" -exec awk 'BEGIN {FS=",";} {if (NF == 4) {if (match($4,"MASTER=")){split($4, tokens, " "); instances[substr(tokens[1], 2)];}}} END {for (element in instances) {print element;}}' '{}' \; | sort --unique

Another way

Another way to do similar functionality would be the following


find /ServerLogs/ \
    -iname "2016_*_*.log" \
    -ipath "/ServerLogs/*/webapi/*" \
    -exec sh -c '
        grep "MASTER=" -s "$0" | awk "BEGIN {FS=\",\";} NF==4" | cut -d "," -f4 | cut -c 3- | cut -d " " -f1 | sort --unique
    ' \
    '{}' \; | sort --unique;

What we changed is the -exec part. Instead of calling a awk script, we create a new sub-shell using sh -c, then we define the source to be executed inside the single codes and we pass as the first parameter of the shell the filename that matched.

Inside the shell, we find all lines that contain the string MASTER= using the grep command. Later we filter out all lines that do not have four columns when we tokenize using the comma character using awk. Then, we get the 4th column using cut and delimiter the comma. We remove the first two characters of the input string using cut -c 3- and later we get only the first column by reusing cut and changing the delimiter to be the space character. With those results we perform a sort that eliminates duplicates and we pass the results to the parent process to perform other operations.

Following is the same code in one line


find /ServerLogs/ -iname "2016_*_*.log" -ipath "/ServerLogs/*/webapi/*" -exec sh -c 'grep "MASTER=" -s "$0" | awk "BEGIN {FS=\",\";} NF==4" | cut -d "," -f4 | cut -c 3- | cut -d " " -f1 | sort --unique' '{}' \; | sort --unique;

C: Split a buffer to a list of segments of a specific size in bits

 in C  tagged bit / bytes / split by

[download id=”2765″]

The following code will split a buffer in C to a list of segments.
The size of the segments does not have to be a multiple of a byte.
User defines the size of the segments in bits when calling node_t *segment(const unsigned char buffer[], const unsigned int buffer_bytes_size, const unsigned int segment_bit_size, const unsigned int first_segment_bit_size);.

Each segment is an instance of element_t structure as follows:

struct element_t {
  unsigned char *segment;
  unsigned int unused_bits;
  unsigned int size;
};

Variable unused_bits defines the bits in the last byte that should not be used in future operations.

[download id=”2765″]

Following is the code that performs the segmentation:

#include "segmentation.h"

#include <math.h>
#include <limits.h>
#include <malloc.h>
#include <string.h>

//This method will create a string made of 0s and 1s representing the bits in an object.
//It will skip printing the last n bits as per the input
char *create_bit_representation_string(const void *object, const unsigned int size,
                                       const unsigned int skip_last_bits)
{
    unsigned int i = 0;
    const unsigned char *byte;
    unsigned int temp_size = size;
    const double mask_filter = pow(2, skip_last_bits);
    const unsigned int skip_last_bytes = skip_last_bits / CHAR_BIT;
    char *result = malloc(sizeof(char) * size * CHAR_BIT - skip_last_bits + 1);

    for (byte = object; temp_size--; ++byte)
    {
        unsigned char mask;
        for (mask = 1 << (CHAR_BIT - 1); mask; mask >>= 1)
        {
            //We do not want to print the last n bits of the last byte as they should always be 0
            if ((temp_size < skip_last_bytes) || (temp_size == 0 && mask < mask_filter))
            {
                break;
            }
            result[i++] = (char) (mask & *byte ? '1' : '0');
        }
    }

    result[i] = '\0';
    return result;
}

//Creating a mask where the first n bits are 1s and the rest are 0s to zero the unused bits of the segment
unsigned char create_left_mask(const unsigned int bits)
{

    unsigned char left_mask = 0;
    unsigned int i;
    for (i = 0; i < bits; i++)
    {
        left_mask |= (1 << (CHAR_BIT - 1 - i));
    }
    return left_mask;
}

//This function will shift to the left a char array for up to 7 bits.
//It will update the object and return the number of bits shifted
unsigned int
shift_left_char_array_n_bits(void *object, const unsigned int size, const unsigned int bits)
{
    if (bits == 0)
    {
        return 0;
    }

    if (bits < 1 || bits > CHAR_BIT - 1)
    {
        fprintf(stderr, "%s: Bad value %u for 'bits', it should be [1,7]"
                "\n\tIgnoring operation\n", __FUNCTION__, bits);
        return 0;
    }

    //Creating a mask where the first n bits are 1s and the rest are 0s.
    const unsigned char left_mask = create_left_mask(bits);

    unsigned char *byte;
    unsigned int temp_size = size;
    //We use temp_size as a counter (until it reaches 0) and we move the byte pointer at each loop
    for (byte = object; temp_size--; ++byte)
    {
        unsigned char carry = 0;
        if (temp_size)
        {
            //We get the bits we want to carry using the mask
            carry = byte[1] & left_mask;
            //Then shift them to the right, as this is where they will be in the new byte.
            carry >>= (CHAR_BIT - bits);
        }
        //Shifting the new byte to make space for the carry
        *byte <<= bits;
        //Applying carry
        *byte |= carry;
    }
    return bits;
}

const unsigned int calculate_unused_bits(const unsigned int segment_bit_size)
{
    return (CHAR_BIT - (segment_bit_size % CHAR_BIT)) % CHAR_BIT;
}

element_t *create_element(const unsigned char buffer[], const unsigned int byte_size,
                          const unsigned int unused_bits, const unsigned int bytes_skipped,
                          const unsigned char left_mask)
{
    element_t *element = (element_t *) malloc(sizeof(element_t));
    element->segment = malloc(byte_size);
    element->size = byte_size;
    element->unused_bits = unused_bits;
    memcpy(element->segment, &(buffer[bytes_skipped]), byte_size);
    //Zeroing the unused bits at the end of the segment
    element->segment[byte_size - 1] &= left_mask;
    return element;
}

//This method will split a buffer to segments of specific size in bits and it will return them as a list
//(each element contains the segment data, its size in bytes and the number of bits that are not used from the last byte)
//If the input buffer is less than the segment size, it will return one segment with all the data.
//The user can set the bit size of the first segment to be different than the rest using first_segment_bit_size > 0
node_t *segment(const unsigned char buffer[], const unsigned int buffer_bytes_size,
                const unsigned int segment_bit_size, const unsigned int first_segment_bit_size)
{
    if (buffer_bytes_size == 0)
    {
        fprintf(stderr, "%s: Bad value %u for 'buffer_bytes_size', it should be greater than 0"
                "\n\tIgnoring operation\n", __FUNCTION__, buffer_bytes_size);
        return NULL;
    }
    if (segment_bit_size == 0)
    {
        fprintf(stderr, "%s: Bad value %u for 'segment_bit_size', it should be greater than 0"
                "\n\tIgnoring operation\n", __FUNCTION__, segment_bit_size);
        return NULL;
    }

    node_t *head = NULL;

    const double char_bit = CHAR_BIT;
    const unsigned int first_segment_byte_size = (unsigned int) ceil(
            first_segment_bit_size / char_bit);
    if (first_segment_byte_size > buffer_bytes_size)
    {
        append(&head, create_element(buffer, buffer_bytes_size, 0, 0, UCHAR_MAX));
        return head;
    }

    unsigned char *temp_buffer = malloc(buffer_bytes_size);
    memcpy(temp_buffer, buffer, buffer_bytes_size);

    unsigned int bits_shifted = 0;
    unsigned int bytes_skipped = 0;

    if (first_segment_bit_size > 0)
    {
        const unsigned int first_segment_unused_bits = calculate_unused_bits(
                first_segment_bit_size);
        const unsigned int first_segment_byte_size_without_incomplete_byte =
                first_segment_bit_size / CHAR_BIT;

        const unsigned int first_segment_bits = CHAR_BIT - first_segment_unused_bits;
        const unsigned char left_mask = create_left_mask(first_segment_bits);

        append(&head, create_element(temp_buffer, first_segment_byte_size,
                                     first_segment_unused_bits, bytes_skipped, left_mask));

        bytes_skipped += first_segment_byte_size_without_incomplete_byte;

        if (bytes_skipped == buffer_bytes_size)
        {
            free(temp_buffer);
            return head;
        }
        if (first_segment_bits > 0 && first_segment_bits < CHAR_BIT)
        {
            bits_shifted += shift_left_char_array_n_bits(&(temp_buffer[bytes_skipped]),
                                                         buffer_bytes_size - bytes_skipped -
                                                         (bits_shifted / CHAR_BIT),
                                                         first_segment_bits);
        }
    }

    const unsigned int segment_byte_size = (unsigned int) ceil(segment_bit_size / char_bit);
    const unsigned int buffer_bits_size =
            (buffer_bytes_size - bytes_skipped) * CHAR_BIT - bits_shifted;
    const unsigned int segments_count = buffer_bits_size / segment_bit_size;

    if (segments_count == 0)
    {
        append(&head, create_element(temp_buffer, buffer_bytes_size - bytes_skipped, bits_shifted, bytes_skipped, UCHAR_MAX));
        free(temp_buffer);
        return head;
    }

    //Creating a mask where first n bits are 1s and the rest are 0s to zero the unused bits of the segment
    const unsigned int segment_unused_bits = calculate_unused_bits(segment_bit_size);
    const unsigned int last_segment_bits = CHAR_BIT - segment_unused_bits;
    const unsigned char left_mask = create_left_mask(last_segment_bits);
    const unsigned int segment_byte_size_without_incomplete_byte = segment_bit_size / CHAR_BIT;
    const unsigned int extra_bits = buffer_bits_size % segment_bit_size;

    unsigned int i;
    for (i = 0; i < segments_count; i++)
    {
        append(&head,
               create_element(temp_buffer, segment_byte_size, segment_unused_bits, bytes_skipped,
                              left_mask));
        bytes_skipped += segment_byte_size_without_incomplete_byte;

        if ((segments_count > 1 || extra_bits > 0) &&
            (last_segment_bits > 0 && last_segment_bits < CHAR_BIT))
        {
            bits_shifted += shift_left_char_array_n_bits(&(temp_buffer[bytes_skipped]),
                                                         buffer_bytes_size - bytes_skipped -
                                                         (bits_shifted / CHAR_BIT),
                                                         last_segment_bits);
        }
    }

    if (extra_bits)
    {
        const unsigned int last_segment_bytes_size =
                buffer_bytes_size - bytes_skipped - (bits_shifted / CHAR_BIT);
        const unsigned int unused_bytes_for_last_segment =
                segment_byte_size - last_segment_bytes_size;
        const unsigned int last_segment_unused_bits =
                segment_bit_size - (buffer_bits_size % segment_bit_size) + segment_unused_bits -
                (unused_bytes_for_last_segment * CHAR_BIT);
        append(&head, create_element(temp_buffer, last_segment_bytes_size,
                                     last_segment_unused_bits, bytes_skipped, UCHAR_MAX));
    }

    free(temp_buffer);
    return head;
}

Sample code that uses the function:

#include <stdio.h>
#include <malloc.h>
#include <string.h>
#include <limits.h>
#include <stdlib.h>
#include <time.h>

#include "libs/segmentation/segmentation.h"


// This application will create a char array of size BUFFER_BYTE_SIZE that contains random values
// and later it will split it in segments of size SEGMENT_BIT_SIZE.
// The first segment will be of size FIRST_SEGMENT_BIT_SIZE.

#define BUFFER_BYTE_SIZE 420
#define SEGMENT_BIT_SIZE 222
#define FIRST_SEGMENT_BIT_SIZE 11
#define POSSIBLE_VALUES 256

int main()
{
    srand(time(NULL));
    const unsigned int buffer_byte_size = BUFFER_BYTE_SIZE;
    fprintf(stdout, "Buffer Size: %uB\n", buffer_byte_size);
    const unsigned int segment_bit_size = SEGMENT_BIT_SIZE;
    fprintf(stdout, "Segment Size: %ub\n", segment_bit_size);
    const unsigned int first_segment_bit_size = FIRST_SEGMENT_BIT_SIZE;
    fprintf(stdout, "First Segment Size: %ub\n", first_segment_bit_size);
    unsigned char buffer[buffer_byte_size];
    unsigned int i;
    for (i = 0; i < buffer_byte_size; i++)
    {
        buffer[i] = (unsigned char) (rand() % POSSIBLE_VALUES);
    }
    char *buffer_bits = create_bit_representation_string(buffer, buffer_byte_size, 0);
    const size_t buffer_length = strlen(buffer_bits);
    fprintf(stdout, "\tBuffer: '%s'\n", buffer_bits);
    node_t *head = segment(buffer, buffer_byte_size, segment_bit_size, first_segment_bit_size);

    element_t *element = pop(&head);
    unsigned int bytes_skipped = 0;
    unsigned int segment_count = 0;
    unsigned int total_segment_bit_size = 0;
    while (element != NULL)
    {

        char *segment_bits = create_bit_representation_string(element->segment,
                                                              element->size,
                                                              element->unused_bits);
        const size_t segment_length = strlen(segment_bits);
        fprintf(stdout,
               "\t\tSegment %04u: Size in bytes %02u - Unused bits %04u - '%.*s'\n",
               ++segment_count,
               element->size, element->unused_bits,
               element->size * CHAR_BIT - element->unused_bits, segment_bits);
        if (segment_length == 0)
        {
            fprintf(stderr,
                    "Data validation failed."
                            "\n\tBuffer size in bytes %d"
                            "\n\tSegment size in bits %d"
                            "\n\tFirst Segment size in bits %d"
                            "\n\tFound empty segment\n",
                    buffer_byte_size, segment_bit_size, first_segment_bit_size);
            clear(&head);
            free(segment_bits);
            free(element->segment);
            free(element);
            free(buffer_bits);
            return EXIT_FAILURE;
        }
        for (i = 0; i < segment_length && bytes_skipped + i < buffer_length; i++)
        {
            if (segment_bits[i] != buffer_bits[bytes_skipped + i])
            {
                fprintf(stderr,
                        "Data validation failed."
                                "\n\tBuffer size in bytes %d"
                                "\n\tSegment size in bits %d"
                                "\n\tFirst Segment size in bits %d"
                                "\n\tPosition %u of the buffer"
                                "\n\tPosition %u of the segment\n",
                        buffer_byte_size, segment_bit_size, first_segment_bit_size, bytes_skipped + i, i);
                clear(&head);
                free(segment_bits);
                free(element->segment);
                free(element);
                free(buffer_bits);
                return EXIT_FAILURE;
            }
        }
        free(segment_bits);
        bytes_skipped += segment_length;

        const unsigned int current_segment_bit_size = ((element->size - 1) * CHAR_BIT) + CHAR_BIT - element->unused_bits;
        if (segment_length != current_segment_bit_size)
        {
            fprintf(stderr,
                    "Data validation failed."
                            "\n\tBuffer size in bytes %d"
                            "\n\tSegment size in bits %d"
                            "\n\tFirst Segment size in bits %d"
                            "\n\tCurrent Segment bit size (%u) not equal to its string representation (%lu)\n",
                    buffer_byte_size, segment_bit_size, first_segment_bit_size, current_segment_bit_size, segment_length);
            clear(&head);
            free(segment_bits);
            free(element->segment);
            free(element);
            free(buffer_bits);
            return EXIT_FAILURE;
        }
        total_segment_bit_size += current_segment_bit_size;

        free(element->segment);
        free(element);
        element = pop(&head);
    }

    free(buffer_bits);

    if (buffer_length != total_segment_bit_size) {
        fprintf(stderr,
                "Data validation failed."
                        "\n\tBuffer size in bytes %d"
                        "\n\tSegment size in bits %d"
                        "\n\tFirst Segment size in bits %d"
                        "\n\tTotal Segment bit size (%u) not equal to full string representation (%lu)\n",
                buffer_byte_size, segment_bit_size, first_segment_bit_size, total_segment_bit_size, buffer_length);
        return EXIT_FAILURE;
    }
    return EXIT_SUCCESS;
}

[download id=”2765″]