Merge pull request #8 from AnswerDotAI/local-first

look at local files first

Author: jph00

llms_txt/_modidx.py

@@ -10,6 +10,8 @@
                                'llms_txt.core._parse_llms': ('core.html#_parse_llms', 'llms_txt/core.py'),
                                'llms_txt.core._section': ('core.html#_section', 'llms_txt/core.py'),
                                'llms_txt.core.create_ctx': ('core.html#create_ctx', 'llms_txt/core.py'),
+                               'llms_txt.core.find_root_dir': ('core.html#find_root_dir', 'llms_txt/core.py'),
+                               'llms_txt.core.get_doc_content': ('core.html#get_doc_content', 'llms_txt/core.py'),
                                'llms_txt.core.get_sizes': ('core.html#get_sizes', 'llms_txt/core.py'),
                                'llms_txt.core.llms_txt2ctx': ('core.html#llms_txt2ctx', 'llms_txt/core.py'),
                                'llms_txt.core.mk_ctx': ('core.html#mk_ctx', 'llms_txt/core.py'),

llms_txt/core.py

@@ -3,7 +3,8 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/01_core.ipynb.
 
 # %% auto 0
-__all__ = ['opt_re', 'named_re', 'search', 'parse_link', 'parse_llms_file', 'mk_ctx', 'get_sizes', 'create_ctx', 'llms_txt2ctx']
+__all__ = ['opt_re', 'named_re', 'search', 'parse_link', 'parse_llms_file', 'find_root_dir', 'get_doc_content', 'mk_ctx',
+           'get_sizes', 'create_ctx', 'llms_txt2ctx']
 
 # %% ../nbs/01_core.ipynb
 import re
@@ -13,6 +14,7 @@
 from fastcore.xml import *
 from fastcore.script import *
 import httpx
+from urllib.parse import urlparse
 
 # %% ../nbs/01_core.ipynb
 def opt_re(s):
@@ -65,14 +67,40 @@ def parse_llms_file(txt):
 # %% ../nbs/01_core.ipynb
 from fastcore.xml import Sections,Project,Doc
 
+# %% ../nbs/01_core.ipynb
+def find_root_dir():
+    "Find the root directory of the nbdev project by looking for settings.ini"
+    path = Path.cwd()
+    while path != path.parent:
+        if (path / 'settings.ini').exists(): return path
+        path = path.parent
+    return None
+
+# %% ../nbs/01_core.ipynb
+def get_doc_content(url):
+    "Fetch content from local file if in nbdev repo."
+    root_dir = find_root_dir()
+    if root_dir:
+        config = Config(root_dir, 'settings.ini')
+        doc_host = config.get('doc_host')
+        if doc_host and url.startswith(doc_host):
+            parsed_url = urlparse(url)
+            relative_path = parsed_url.path.lstrip('/')
+            local_path = root_dir / '_docs' / relative_path
+            if local_path.exists():
+                with open(local_path, 'r') as f: return f.read()
+    # If not a local file or file doesn't exist, fetch from URL
+    return httpx.get(url).text
+
 # %% ../nbs/01_core.ipynb
 def _doc(kw):
     "Create a `Doc` FT object with the text retrieved from `url` as the child, and `kw` as attrs."
     url = kw.pop('url')
+    txt = get_doc_content(url)
     re_comment = re.compile('^<!--.*-->$', flags=re.MULTILINE)
     re_base64_img = re.compile(r'<img[^>]*src="data:image/[^"]*"[^>]*>')
-    txt = [o for o in httpx.get(url).text.splitlines() if not re_comment.search(o) and not re_base64_img.search(o)]
-    return Doc('\n'.join(txt), **kw)
+    txt = '\n'.join([o for o in txt.splitlines() if not re_comment.search(o) and not re_base64_img.search(o)])
+    return Doc(txt, **kw)
 
 # %% ../nbs/01_core.ipynb
 def _section(nm, items, n_workers=None):

nbs/01_core.ipynb

@@ -49,7 +49,8 @@
     "from fastcore.utils import *\n",
     "from fastcore.xml import *\n",
     "from fastcore.script import *\n",
-    "import httpx"
+    "import httpx\n",
+    "from urllib.parse import urlparse"
    ]
   },
   {
@@ -673,6 +674,45 @@
     "from fastcore.xml import Sections,Project,Doc"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "def find_root_dir():\n",
+    "    \"Find the root directory of the nbdev project by looking for settings.ini\"\n",
+    "    path = Path.cwd()\n",
+    "    while path != path.parent:\n",
+    "        if (path / 'settings.ini').exists(): return path\n",
+    "        path = path.parent\n",
+    "    return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#|export\n",
+    "def get_doc_content(url):\n",
+    "    \"Fetch content from local file if in nbdev repo.\"\n",
+    "    root_dir = find_root_dir()\n",
+    "    if root_dir:\n",
+    "        config = Config(root_dir, 'settings.ini')\n",
+    "        doc_host = config.get('doc_host')\n",
+    "        if doc_host and url.startswith(doc_host):\n",
+    "            parsed_url = urlparse(url)\n",
+    "            relative_path = parsed_url.path.lstrip('/')\n",
+    "            local_path = root_dir / '_docs' / relative_path\n",
+    "            if local_path.exists():\n",
+    "                with open(local_path, 'r') as f: return f.read()\n",
+    "    # If not a local file or file doesn't exist, fetch from URL\n",
+    "    return httpx.get(url).text"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -683,10 +723,11 @@
     "def _doc(kw):\n",
     "    \"Create a `Doc` FT object with the text retrieved from `url` as the child, and `kw` as attrs.\"\n",
     "    url = kw.pop('url')\n",
+    "    txt = get_doc_content(url)\n",
     "    re_comment = re.compile('^<!--.*-->$', flags=re.MULTILINE)\n",
     "    re_base64_img = re.compile(r'<img[^>]*src=\"data:image/[^\"]*\"[^>]*>')\n",
-    "    txt = [o for o in httpx.get(url).text.splitlines() if not re_comment.search(o) and not re_base64_img.search(o)]\n",
-    "    return Doc('\\n'.join(txt), **kw)"
+    "    txt = '\\n'.join([o for o in txt.splitlines() if not re_comment.search(o) and not re_base64_img.search(o)])\n",
+    "    return Doc(txt, **kw)"
    ]
   },
   {