


chatGPT - C programming Linux Windows cross-platform - code review request
I have been meddling with using chatGPT prompts to program in C.
Using incremental prompts it is possible to get chatGPT 3.5 to do a lot more than expected.
I wonder about code quality and would enjoy feedback both on prompts and code.
Function objective
- verify a path is valid and parse the path components
- MacOS Linux Windows cross-platform compatibility
Implementation
thread safe code
static path
dynamic path allocation for larger path string
Standard practice for Linux / MacOs is to dynamically allocate (4095 / 1024 chart path limit), whereas Windows (260 path limit) is to statically allocate.
Prompt
I incrementally build up the query, otherwise chatGPT tends to unlearn previous request changes.
In the end this looks like some crude form of meta coding where it is possible to coerce the LLM to generate the desired code.
_query LLM perplexity.ai Modify code example Portable Path Parsing and Validation Code in C use thread safe function use function pointer strtok_s() for Windows strtok_r() for linux allocate INITIAL_BUFFER_SIZE 60 char static path_copy declare pointer pfinal_path_copy initialize to path_copy when necessary dynamically allocate final_path_copy pfinal_path_copy = final_path_copy use single strcpy(pfinal_path_copy, path) function
Code is shaped one feature at a time to match the desired style
modify example replace 60 by equate
Some prompts remained sticky without being repeated. "no WSL cygwin" was added early on to prompt for Windows OS specific code, then dropped.
write code example parse path in portable way linux windows MacOS no WSL cygwin
Code
Resulting code compiles and runs on the first go.
#include <stdio.h> #include <stdlib.h> #include <string.h> #ifdef _WIN32 #include <io.h> // For _access() on Windows #include <windows.h> // For Windows API #else #include <unistd.h> // For access() on Unix-like systems (Linux, macOS) #include <sys/stat.h> #endif // Define a constant for the initial buffer size #define INITIAL_BUFFER_SIZE 60 // Function to check if a path is valid int path_validate(const char *path) { #ifdef _WIN32 return _access(path, 0) == 0; // 0 means the file exists #else struct stat buffer; return (stat(path, &buffer) == 0); // Returns 1 if valid, 0 if invalid #endif } // Type definition for tokenization function pointer typedef char* (*tokenizer_func)(char*, const char*, char**); // Function to parse the path into components void parse_path(const char *path) { char path_copy[INITIAL_BUFFER_SIZE]; // Static buffer for initial use char *final_path_copy = NULL; // Pointer for dynamic allocation char *pfinal_path_copy = path_copy; // Pointer to point to either path_copy or final_path_copy // Check if the input path length exceeds INITIAL_BUFFER_SIZE if (strlen(path) + 1 > INITIAL_BUFFER_SIZE) { final_path_copy = malloc(strlen(path) + 1); // Dynamically allocate memory if (final_path_copy == NULL) { fprintf(stderr, "Memory allocation failed.\n"); exit(EXIT_FAILURE); } pfinal_path_copy = final_path_copy; // Point to dynamically allocated memory } // Use a single strcpy function to copy the path into the appropriate buffer strcpy(pfinal_path_copy, path); // Copy full path into the selected buffer // Determine the separator based on the platform and assign the tokenizer function const char *separator; tokenizer_func tokenizer; char *saveptr; #ifdef _WIN32 separator = "\"; tokenizer = strtok_s; // Use strtok_s for Windows #else separator = "/"; tokenizer = strtok_r; // Use strtok_r for Linux #endif // Tokenize using the assigned tokenizer function char *token = tokenizer(pfinal_path_copy, separator, &saveptr); while (token != NULL) { printf("Path component: %s\n", token); token = tokenizer(NULL, separator, &saveptr); // Continue tokenizing } free(final_path_copy); // Free dynamically allocated memory after use (if allocated) } int main(int argc, char *argv[]) { if (argc < 2) { fprintf(stderr, "Usage: %s <path>\n", argv[0]); return EXIT_FAILURE; } const char *path = argv[1]; // Validate the path using the new function name if (path_validate(path)) { printf("The path '%s' is valid.\n", path); printf("Parsing components:\n"); parse_path(path); } else { printf("The path '%s' is invalid.\n", path); } return EXIT_SUCCESS; } ## Unit test Was created but not included here ## Performance The entire exercise took 2:30 hour. I have not tested the code on Windows or MacOS. I'd like some feedback on code quality.
The above is the detailed content of chatGPT - C programming Linux Windows cross-platform - code review request. For more information, please follow other related articles on the PHP Chinese website!

Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Article

Hot Tools

Notepad++7.3.1
Easy-to-use and free code editor

SublimeText3 Chinese version
Chinese version, very easy to use

Zend Studio 13.0.1
Powerful PHP integrated development environment

Dreamweaver CS6
Visual web development tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

Hot Topics











The history and evolution of C# and C are unique, and the future prospects are also different. 1.C was invented by BjarneStroustrup in 1983 to introduce object-oriented programming into the C language. Its evolution process includes multiple standardizations, such as C 11 introducing auto keywords and lambda expressions, C 20 introducing concepts and coroutines, and will focus on performance and system-level programming in the future. 2.C# was released by Microsoft in 2000. Combining the advantages of C and Java, its evolution focuses on simplicity and productivity. For example, C#2.0 introduced generics and C#5.0 introduced asynchronous programming, which will focus on developers' productivity and cloud computing in the future.

There are significant differences in the learning curves of C# and C and developer experience. 1) The learning curve of C# is relatively flat and is suitable for rapid development and enterprise-level applications. 2) The learning curve of C is steep and is suitable for high-performance and low-level control scenarios.

The application of static analysis in C mainly includes discovering memory management problems, checking code logic errors, and improving code security. 1) Static analysis can identify problems such as memory leaks, double releases, and uninitialized pointers. 2) It can detect unused variables, dead code and logical contradictions. 3) Static analysis tools such as Coverity can detect buffer overflow, integer overflow and unsafe API calls to improve code security.

C interacts with XML through third-party libraries (such as TinyXML, Pugixml, Xerces-C). 1) Use the library to parse XML files and convert them into C-processable data structures. 2) When generating XML, convert the C data structure to XML format. 3) In practical applications, XML is often used for configuration files and data exchange to improve development efficiency.

Using the chrono library in C can allow you to control time and time intervals more accurately. Let's explore the charm of this library. C's chrono library is part of the standard library, which provides a modern way to deal with time and time intervals. For programmers who have suffered from time.h and ctime, chrono is undoubtedly a boon. It not only improves the readability and maintainability of the code, but also provides higher accuracy and flexibility. Let's start with the basics. The chrono library mainly includes the following key components: std::chrono::system_clock: represents the system clock, used to obtain the current time. std::chron

The future of C will focus on parallel computing, security, modularization and AI/machine learning: 1) Parallel computing will be enhanced through features such as coroutines; 2) Security will be improved through stricter type checking and memory management mechanisms; 3) Modulation will simplify code organization and compilation; 4) AI and machine learning will prompt C to adapt to new needs, such as numerical computing and GPU programming support.

C isnotdying;it'sevolving.1)C remainsrelevantduetoitsversatilityandefficiencyinperformance-criticalapplications.2)Thelanguageiscontinuouslyupdated,withC 20introducingfeatureslikemodulesandcoroutinestoimproveusabilityandperformance.3)Despitechallen

C# uses automatic garbage collection mechanism, while C uses manual memory management. 1. C#'s garbage collector automatically manages memory to reduce the risk of memory leakage, but may lead to performance degradation. 2.C provides flexible memory control, suitable for applications that require fine management, but should be handled with caution to avoid memory leakage.
