Finished 'idxtool' features

- added alphabetical IDs sort in TOC generation
- implemented multi-find 'findgpt' command line for the idxtool (it supports URLs, IDs, or response files)

.scripts/README.md

@@ -2,68 +2,71 @@
 
 The `idxtool` is a GPT indexing and searching tool for the CSP repo (ChatGPT System Prompt).
 
+Contributions to `idxtool` are welcome. Please submit pull requests or issues to the CSP repo for review.
+
 ## Command line
 
 ```
-usage: idxtool.py [-h] [--update-logo UPDATE_LOGO] [--toc [TOC]]
-                  [--update-description UPDATE_DESCRIPTION]
-                  [--find-gptfile FIND_GPTFILE] [--find-gpttoc FIND_GPTTOC]
-                  [--parse-gptfile PARSE_GPTFILE] [--rename RENAME]
+usage: idxtool.py [-h] [--toc [TOC]] [--find-gpt FIND_GPT] 
+                  [--parse-gptfile PARSE_GPTFILE] [--rename]
 
 idxtool: A GPT indexing and searching tool for the CSP repo
 
 options:
   -h, --help            show this help message and exit
-  --update-logo UPDATE_LOGO
-                        Update the logos of the GPT file
   --toc [TOC]           Rebuild the table of contents (TOC.md) file
-  --update-description UPDATE_DESCRIPTION
-                        Update the descriptions of the GPT file
-  --find-gptfile FIND_GPTFILE
-                        Find a GPT by its ID or name
-  --find-gpttoc FIND_GPTTOC
-                        Searches the TOC.md file for the given gptid or free
-                        style string
+  --find-gpt FIND_GPT
+                        Find a GPT file by its ID or full ChatGPT URL
   --parse-gptfile PARSE_GPTFILE
                         Parses a GPT file name
-  --rename              Rename all the GPT file names to include their GPT ID
+  --rename              Rename the GPT file names to include their GPT ID
 ```
 
 ## Features
 
-- Update Logos: Use `--update-logo [filename]` to update the logos of the GPT file.
 - Rebuild TOC: Use `--toc` to rebuild the table of contents (TOC.md) file.
-- Update Descriptions: Use `--update-description [filename]` to update the descriptions of the GPT file.
-- Find GPT File: Use `--find-gptfile [gptid or gpt name in quotes]` to find a GPT by its ID or name.
-- Find GPT in TOC: Use `--find-gpttoc [gptid or string]` to search the TOC.md file for a given gptid or free style string.
+- Find GPT File: Use `--find-gpt [GPTID or Full ChatGPT URL or a response file with IDs/URLs]` to find a GPT by its ID or URL.
 - Rename GPT: Use `--rename` to rename all the GPTs to include their GPTID as prefix.
 - Help: Use `--help` to display the help message and usage instructions.
 
-## Usage
+## Example
 
-To use the tool, run the following command in your terminal with the appropriate arguments:
+To rebuild the [TOC.md](../TOC.md) file, run:
 
 ```bash
-python idxtool.py [arguments]
+python idxtool.py --toc
 ```
 
-Replace `[arguments]` with one of the feature commands listed above.
+To find a GPT by its ID, run:
 
-## Example
+```bash
+python idxtool.py --find-gpt 3rtbLUIUO
+```
 
-To update the logos of a GPT file named `example_gpt.json`, run:
+or by URL:
+
+```bash
+python idxtool.py --find-gpt https://chat.openai.com/g/g-svehnI9xP-retro-adventures
+```
+
+Additionally, you can have a file with a list of IDs or URLs and pass it to the `--find-gpt` option:
 
 ```bash
-python idxtool.py --update-logo example_gpt.json
+python idxtool.py --find-gpt @gptids.txt
 ```
 
-## Installation
+(note the '@' symbol).
 
-No additional installation is required. Ensure that you have Python installed on your system to run the tool.
+The `gptids.txt` file contains a list of IDs or URLs, one per line:
 
-## Contributing
+```text
+3rtbLUIUO
+https://chat.openai.com/g/g-svehnI9xP-retro-adventures
+#vYzt7bvAm
+w2yOasK1r
+waDWNw2J3
+```
 
-Contributions to `idxtool` are welcome. Please submit pull requests or issues to the CSP repo for review.
 
 ## License
 

.scripts/gptparser.py

@@ -6,15 +6,17 @@
 
 import os, re
 from collections import namedtuple
-from typing import Union, Tuple, Generator
+from typing import Union, Tuple, Generator, Iterator
 
-compiled_pattern = re.compile(r'^([0-9a-z]{9})_([^\.]+)\.md$', re.IGNORECASE)
 
 GPT_BASE_URL = 'https://chat.openai.com/g/g-'
 GPT_BASE_URL_L = len(GPT_BASE_URL)
 FIELD_PREFIX = 'GPT'
 
+GPT_FILE_ID_RE = re.compile(r'^([0-9a-z]{9})_(.*)\.md$', re.IGNORECASE)
+"""GPT file name regex with ID and name capture."""
 GPT_FILE_VERSION_RE = re.compile(r'\[([^]]*)\]\.md$', re.IGNORECASE)
+"""GPT file name regex with version capture."""
 
 GptFieldInfo = namedtuple('FieldInfo', ['order', 'display'])
 
@@ -149,19 +151,15 @@ def enum_gpts() -> Generator[Tuple[bool, Union[GptMarkdownFile, str]], None, Non
         else:
             yield (False, f"Failed to parse '{file_path}': {gpt}")
 
-def enum_gpt_files() -> Generator[str, None, None]:
+def enum_gpt_files() -> Iterator[Tuple[str, str]]:
     """
     Enumerate all the GPT files in the prompts directory while relying on the files naming convention.
     To normalize all the GPT file names, run the `idxtool.py --rename`
     """
-    pattern = r'[a-z]{9}_[a-z]+\.[a-z]+'
-
     prompts_path = get_prompts_path()
     for file_path in os.listdir(prompts_path):
-        _, ext = os.path.splitext(file_path)
-        if ext != '.md':
+        m = GPT_FILE_ID_RE.match(file_path)
+        if not m:
             continue
         file_path = os.path.join(prompts_path, file_path)
-        yield file_path
-
-
+        yield (m.group(1), file_path)

.scripts/idxtool.py

@@ -1,14 +1,14 @@
 """
 idxtool is a script is used to perform various GPT indexing and searching tasks
 
-- Reformat all the GPT files in the source path and save them to the destination path.
+- Find a GPT file by its ID or full ChatGPT URL or via a file containing a list of GPT IDs.
 - Rename all the GPTs to include their ChatGPT/g/ID in the filename.
 - Generate TOC
 - etc.
 """
 
 import sys, os, argparse
-from gptparser import GptMarkdownFile, enum_gpts, parse_gpturl
+from gptparser import GptMarkdownFile, enum_gpts, parse_gpturl, enum_gpt_files
 from typing import Tuple
 from urllib.parse import quote
 
@@ -18,20 +18,6 @@
 def get_toc_file() -> str:
     return os.path.abspath(os.path.join(os.path.dirname(__file__), '..', TOC_FILENAME))    
 
-def update_logo(filename):
-    if filename == '*':
-        print("TODO: Updating logo for all GPT files")
-    else:
-        print(f"TODO: Updating logo with file: {filename}")
-    raise NotImplementedError
-
-def update_description(filename):
-    if filename == '*':
-        print("TODO: Updating description for all GPT files")
-    else:
-        print(f"TODO Updating description with file: {filename}")
-    raise NotImplementedError
-
 def rename_gpts():
     nb_ok = nb_total = 0
     all_renamed_already = True
@@ -117,15 +103,24 @@ def rebuild_toc(toc_out: str = '') -> Tuple[bool, str]:
     out.append(f"{TOC_GPT_MARKER_LINE}\n")
 
     nb_ok = nb_total = 0
+    gpts = []
     for ok, gpt in enum_gpts():
         nb_total += 1
-        if ok and (id := gpt.id()):
-            nb_ok += 1
-            file_link = f"./prompts/gpts/{quote(os.path.basename(gpt.filename))}"
-            version = f" {gpt.get('version')}" if gpt.get('version') else ''
-            out.append(f"  - [{gpt.get('title')}{version} (id: {id.id})]({file_link})\n")
+        if ok:
+            if id := gpt.id():
+                nb_ok += 1
+                gpts.append((id, gpt))
+            else:
+                print(f"[!] No ID detected: {gpt.filename}")
         else:
-            print(f"[!] {gpt.filename}")
+            print(f"[!] {gpt}")
+
+    # Consistently sort the GPTs by ID
+    gpts.sort(key=lambda x: x[0].id)
+    for id, gpt in gpts:
+        file_link = f"./prompts/gpts/{quote(os.path.basename(gpt.filename))}"
+        version = f" {gpt.get('version')}" if gpt.get('version') else ''
+        out.append(f"  - [{gpt.get('title')}{version} (id: {id.id})]({file_link})\n")
 
     ofile.writelines(out)
     ofile.close()
@@ -135,54 +130,69 @@ def rebuild_toc(toc_out: str = '') -> Tuple[bool, str]:
     if ok:
         print(msg)
     return (ok, msg)
-
-def find_gpt_in_toc(gptid_or_string):
-    print(f"TODO: Searching TOC.md for GPT ID or string: {gptid_or_string}")
-    raise NotImplementedError
-
-def find_gptfile(keyword):
-    keyword = keyword.strip().tolower()
+
+def find_gptfile(keyword, verbose=True):
+    """Find a GPT file by its ID or full ChatGPT URL
+    The ID can be prefixed with '@' to indicate a file containing a list of GPT IDs.
+    """
+    keyword = keyword.strip()
     # Response file with a set of GPT IDs
     if keyword.startswith('@'):
-        print(f"TODO: Finding GPT file with ID: {keyword}")
-    if gpt_info := parse_gpturl(keyword):
-        keyword = gpt_info.id
+        with open(keyword[1:], 'r', encoding='utf-8') as file:
+            ids = set()
+            for line in file:
+                line = line.strip()
+                # Skip comments
+                if line.startswith('#'):
+                    continue
+                # If the line is a GPT URL, then extract the ID
+                if gpt_info := parse_gpturl(line):
+                    ids.add(gpt_info.id)
+                    continue
+                # If not a GPT URL, then it's a GPT ID
+                ids.add(line)
+    elif gpt_info := parse_gpturl(keyword):
+        # A single GPT URL
+        ids = {gpt_info.id}
+    else:
+        # A single GPT ID
+        ids = {keyword}
+
+    if verbose:
+        print(f'Looking for GPT files with IDs: {", ".join(ids)}')
+    matches = []
+    for id, filename in enum_gpt_files():
+        if id in ids:
+            if verbose:
+                print(filename)
+            matches.append((id, filename))
+
+    return matches
 
-    print(f"TODO: Finding GPT with ID: {keyword}")
-    raise NotImplementedError
 
 def main():
     parser = argparse.ArgumentParser(description='idxtool: A GPT indexing and searching tool for the CSP repo')
 
-    parser.add_argument('--update-logo', type=str, help='Update the logos of the GPT file')
     parser.add_argument('--toc', nargs='?', const='', type=str, help='Rebuild the table of contents (TOC.md) file')
-    parser.add_argument('--update-description', type=str, help='Update the descriptions of the GPT file')
-    parser.add_argument('--find-gptfile', type=str, help='Find a GPT by its ID or name')
-    parser.add_argument('--find-gpttoc', type=str, help='Searches the TOC.md file for the given gptid or free style string')
+    parser.add_argument('--find-gpt', type=str, help='Find a GPT file by its ID or full ChatGPT URL')
     parser.add_argument('--parse-gptfile', type=str, help='Parses a GPT file name')
     parser.add_argument('--rename', action='store_true', help='Rename the GPT file names to include their GPT ID')
 
     # Handle arguments
     ok = True
 
     args = parser.parse_args()
-    if args.update_logo:
-        update_logo(args.update_logo)
     if args.parse_gptfile:
         ok, err = parse_gpt_file(args.parse_gptfile)
         if not ok:
             print(err)
-    if args.toc is not None:
+    elif args.toc is not None:
         ok, err = rebuild_toc(args.toc)
         if not ok:
             print(err)
-    if args.update_description:
-        update_description(args.update_description)
-    if args.find_gptfile:
-        find_gptfile(args.find_gptfile)
-    if args.find_gpttoc:
-        find_gpt_in_toc(args.find_gpttoc)
-    if args.rename:
+    elif args.find_gpt:
+        find_gptfile(args.find_gpt)
+    elif args.rename:
         ok, err = rename_gpts()
         if not ok:
             print(err)