c - 如何将一行的尾部添加到哈希表中

Question

我正在尝试使用此代码将文件行添加到哈希表。目前它读取格式的文件。

289016164,279211721,462102225
341714666,132189021,299107290
362328497,466836829,47952622

那是三个逗号分隔的行。我希望它能够读取格式的行

289016164,279211721,462102225, some random text
341714666,132189021,299107290, some more random text
362328497,466836829,47952622, even more random text

应该包含每一行的结构应该是

typedef struct Row {
    uint32_t a;
    uint32_t b;
    uint32_t t;
    char text[40];
} Row;

读取文件的例程称为 readAll(见下文)，我在修改它以执行此操作时遇到问题。

How can I change readAll to be able to cope with this new format?

我已经包含了大部分使用 readAll 的代码来提供一些上下文。

#include <stdlib.h>
#include <stdio.h>
#include <stdint.h>
#include <string.h>

// Should be 37% occupied with 50m entries
#define TABLE_SIZE 0x8000000
#define MASK (TABLE_SIZE - 1)
#define BUFFER_SIZE 16384
#define END_OF_FILE (-1)
#define DEFAULT_VALUE (-1)

typedef struct Row {
    uint32_t a;
    uint32_t b;
    uint32_t t;
} Row;

int32_t hash(int32_t a) {
    return a * 428916315;
}

void insert(Row * table, Row row) {
    long loc = hash(row.a) & MASK; // Entries are hashed on a
    long inc = 0;
    while (inc <= TABLE_SIZE) {
        loc = (loc + inc) & MASK;
        inc++;
        if (table[loc].a == DEFAULT_VALUE) {
            table[loc] = row;
            break;
        }
    }
}

int readChar(FILE * input, char * buffer, int * pos, int * limit) {
    if (*limit < *pos) {
        return buffer[(*limit)++];
    } else {
        *limit = 0;
        *pos = fread(buffer, sizeof(char), BUFFER_SIZE, input);
        if (*limit < *pos) {
            return buffer[(*limit)++];
        } else
            return END_OF_FILE;
    }
}

void readAll(char * fileName, Row * table) {
    char* buffer = (char*) malloc(sizeof(char) * BUFFER_SIZE);
    int limit = 0;
    int pos = 0;

    FILE * input = fopen(fileName, "rb");

    int lastRead;
    Row currentRow;
    uint32_t * currentElement = &(currentRow.a);

    // We read rows with an FSM. We can
    // roll up some of the code using the `currentElement` pointer
    while (1) {
        switch(lastRead = readChar(input, buffer, &pos, &limit)) {
            case END_OF_FILE:
                fclose(input);
                return;
            case ',':
                if (currentElement == &(currentRow.a))
                    currentElement = &(currentRow.b);
                else
                    currentElement = &(currentRow.t);
                break;
            case '\n':
                insert(table, currentRow);
                currentRow.a = 0;
                currentRow.b = 0;
                currentRow.t = 0;
                currentElement = &(currentRow.a);
                break;
            default:
                *currentElement = *currentElement * 10 + (lastRead - '0');
                break;
        }
    }  //printf("Read %d", lastRead);
}

int main(int argc, char** argv) {
    Row* table = (Row*) malloc(sizeof(Row) * TABLE_SIZE);
    memset(table, 255, sizeof(Row) * TABLE_SIZE);

    readAll(argv[1], table);

    //[...]
}

Answer 1

您需要识别第三个逗号并在找到时填写 .text，大致如下:

        case ',':
            if (currentElement == &(currentRow.a)) {
                currentElement = &(currentRow.b);
                break;
            }
            if (currentElement == &(currentRow.b)) {
                currentElement = &(currentRow.t);
                break;
            }
            {   int i = 0;
                int maxchars = sizeof(currentRow->text) - 1;

                while ((lastRead = readChar(input, buffer, &pos, &limit)) != '\n') {
                    if (i < maxchars) currentRow->text[i++] = lastRead;
                }
                currentRow->text[i] = '\0';
            }
            /* fallthrough*/