Issue eli64s#8 java support for README setup guide.

README.md

@@ -114,31 +114,37 @@ README-AI is a powerful, user-friendly tool that automatically generates high-qu
       <td>1️⃣</td>
       <td><a href="https://github.com/eli64s/README-AI/blob/main/docs/README_EX_1.md">README_1_PY.md</a></td>
       <td><a href="https://github.com/eli64s/readme-ai">readme-ai</a></td>
-      <td><p>15459624</p>
+      <td><p>15,459,624</p>
     </tr>
     <tr>
       <td>2️⃣</td>
       <td><a href="https://github.com/eli64s/README-AI/blob/main/docs/README_EX_2.md">README_2_PY.md</a></td>
       <td><a href="https://github.com/GokuMohandas/mlops-course">mlops-course</a></td>
-      <td><p>8698890</p>
+      <td><p>8,698,890</p>
     </tr>
     <tr>
       <td>3️⃣</td>
       <td><a href="https://github.com/eli64s/README-AI/blob/main/docs/README_EX_JS.md">README_3_JS.md</a></td>
       <td><a href="https://github.com/philnash/react-web-audio">react-web-audio</a></td>
-      <td><p>533233</p>
+      <td><p>533,233</p>
     </tr>
     <tr>
       <td>4️⃣</td>
       <td><a href="https://github.com/eli64s/README-AI/blob/main/docs/README_EX_RUST.md">README_4_RUST.md</a></td>
       <td><a href="https://github.com/MihaiBogdanEugen/contacts-cli">rust-contacts-cli</a></td>
-      <td><p>79104</p>
+      <td><p>79,104</p>
     </tr>
     <tr>
       <td>5️⃣</td>
       <td><a href="https://github.com/eli64s/README-AI/blob/main/docs/README_EX_3.md">README_5_FastAPI.md</a></td>
       <td><a href="https://github.com/nofoobar/JobBoard-Fastapi">job-board-fastapi</a></td>
-      <td><p>75391521</p>
+      <td><p>75,391,521</p>
+    </tr>
+    <tr>
+      <td>6️⃣</td>
+      <td><a href="https://github.com/eli64s/README-AI/blob/main/docs/README_EX_3.md">README_6_JAVA.md</a></td>
+      <td><a href="https://github.com/avjinder/Minimal-Todo">java-minimal-todo</a></td>
+      <td><p>18,240,095</p>
     </tr>
   </table>
 </div>

conf/badges.json

@@ -7344,6 +7344,13 @@
       "color": "white",
       "svg": "M11.591 19.649h.771v-3.786h-.77zm-6.874-5.03l-.238-.733 3.6-1.17.238.735-3.6 1.17m4.645-5.762L7.138 5.796l.624-.453 2.224 3.062-.624.454m5.315.028l-.624-.454 2.225-3.062.624.453-2.225 3.063m4.592 5.78l-3.6-1.17.238-.734 3.6 1.17-.238.733M12 .001C5.383.001 0 5.384 0 11.998 0 18.617 5.383 24 12 24s12-5.382 12-12c0-6.617-5.383-12-12-12zm0 2.43c5.284 0 9.569 4.283 9.569 9.567 0 5.287-4.285 9.573-9.569 9.573-5.286 0-9.57-4.286-9.57-9.573 0-5.284 4.285-9.567 9.57-9.567m1.552 7.96l.575 1.768.747.242 4.736-1.538-.86-2.645-4.736 1.539-.462.635m.337 2.5l-1.504 1.093v.785l2.927 4.03 2.25-1.636-2.927-4.029-.746-.243m-2.275 1.093l-1.504-1.093-.747.243-2.927 4.029 2.25 1.635 2.928-4.029v-.785M9.873 12.16l.574-1.767-.462-.635-4.736-1.54-.86 2.646 4.737 1.54.747-.244m1.198-2.22h1.859l.462-.636v-4.98H10.61v4.98l.461.636"
     },
+    {
+      "name": "Java",
+      "hex": "",
+      "src": "https://img.shields.io/badge/java-%23ED8B00.svg?style=for-the-badge&logo=openjdk&logoColor=white",
+      "color": "",
+      "svg": ""
+    },
     {
       "name": "JavaScript",
       "hex": "F7DF1E",

conf/conf.toml

@@ -1,7 +1,7 @@
 # OpenAI API language model parameters
 [api]
 api_key = ""
-prompt_intro = """Generate a short summary that describes the capabilities of the GitHub project {}."""
+prompt_intro = """Generate a 2-3 sentence summary that describes the capabilities of the GitHub project {}."""
 prompt_slogan = """Generate a slogan for the GitHub project {}."""
 
 # Repository (local and remote)

conf/ignore_files.toml

@@ -51,7 +51,7 @@ ignore = [
     ".ini",
     ".yml",
     ".yaml",
-    ".xml",
+    #".xml",
     ".properties",
     ".secret",
     ".key",

conf/setup_guide.toml

@@ -21,7 +21,7 @@ Forth = ["gforth main.fs"]
 Go = ["go build -o myapp", "./myapp"]
 Groovy = ["grape install", "groovy main.groovy"]
 Haskell = ["ghc -o myapp main.hs", "./myapp"]
-Java = ["mvn clean install", "java -jar target/myapp.jar"]
+Java = ["mvn clean install || gradle build", "java -jar target/myapp.jar"]
 JavaScript = ["npm install", "npm start"]
 Julia = ["julia --project -e 'import Pkg; Pkg.instantiate()'", "julia main.jl"]
 Kotlin = ["gradle build", "java -jar build/libs/myapp.jar"]

src/builder.py

@@ -142,7 +142,7 @@ def create_setup_guide(conf: object, conf_helper: object, df: pd.DataFrame):
     conf : object
         Configuration object containing GitHub and markdown configurations.
     conf_helper : object
-        Configuration helper object containing file extensions and setup guides.
+        Configuration helper object containing file extensions and setup guide.
     df : pd.DataFrame
         DataFrame containing parsed information from project files.
 
@@ -159,7 +159,9 @@ def create_setup_guide(conf: object, conf_helper: object, df: pd.DataFrame):
     path = conf.github.path
 
     df["Language"] = df["Module"].apply(
-        lambda x: Path(x).suffix[1:] if Path(x).suffix[1:] not in ignore_files else None
+        lambda x: Path(x).suffix[1:]
+        if Path(x).suffix[1:] not in ignore_files and Path(x).suffix != ".xml"
+        else None
     )
     top_language = df["Language"].value_counts().idxmax()
 
@@ -169,14 +171,14 @@ def create_setup_guide(conf: object, conf_helper: object, df: pd.DataFrame):
 
         LOGGER.info(f"Top project language: {top_language}")
         LOGGER.info(f"Top project language name: {language_name}")
-        LOGGER.info(f"{language_name} installation and setup: {language_setup}")
+        LOGGER.info(f"{language_name} installation & setup: {language_setup}")
 
         if language_setup:
             install_guide = language_setup[0]
             run_guide = language_setup[1]
 
     except KeyError as ke:
-        LOGGER.warning(f"KeyError: {ke}. Using default install and run guides.")
+        LOGGER.warning(f"KeyError: {ke}. Using default install and run guide.")
 
     md_setup_guide = conf.md.setup.format(
         name, path, name, install_guide, name, run_guide
@@ -187,7 +189,8 @@ def create_setup_guide(conf: object, conf_helper: object, df: pd.DataFrame):
 
 def create_directory_tree(url: str) -> str:
     """
-    Creates a directory tree structure of the project based on its repository URL.
+    Creates a directory tree structure for the README.md
+    file based on the provided repository path or URL.
 
     Parameters
     ----------

src/model.py

@@ -10,7 +10,7 @@
 import spacy
 
 from logger import Logger
-from preprocess import format_sentence
+from preprocess import reformat_sentence
 
 ENGINE_ID = "text-davinci-003"
 ENGINE = f"https://api.openai.com/v1/engines/{ENGINE_ID}/completions"
@@ -123,7 +123,7 @@ async def fetch_summary(file_path: str, prompt: str) -> Tuple[str, str]:
         json={
             "prompt": prompt,
             "temperature": 0,
-            "max_tokens": 50,
+            "max_tokens": 69,
             "top_p": 1,
             "frequency_penalty": 0.0,
             "presence_penalty": 0.0,
@@ -144,7 +144,7 @@ async def fetch_summary(file_path: str, prompt: str) -> Tuple[str, str]:
     file_summary = data["choices"][0]["text"]
     summary = re.sub(r"^[^a-zA-Z]*", "", file_summary)
     summary_spacy = spacy_text_processor(summary)
-    summary_spacy = format_sentence(summary_spacy)
+    summary_spacy = reformat_sentence(summary_spacy)
     return (file_path, summary_spacy)
 
 
@@ -166,7 +166,7 @@ def generate_summary_text(prompt: str) -> str:
     completions = openai.Completion.create(
         engine=ENGINE_ID,
         prompt=prompt,
-        max_tokens=40,
+        max_tokens=69,
     )
     generated_text = completions.choices[0].text
     return generated_text.lstrip()

src/preprocess.py

@@ -139,6 +139,8 @@ def _get_file_parsers() -> Dict[str, callable]:
         A dictionary containing file parsers for various file types.
     """
     return {
+        "build.gradle": helper.parse_gradle,
+        "pom.xml": helper.parse_maven,
         "cargo.toml": helper.parse_cargo_toml,
         "cargo.lock": helper.parse_cargo_lock,
         "go.mod": helper.parse_go_mod,
@@ -251,9 +253,9 @@ def get_repo_name(path: Union[str, Path]) -> str:
     return repo_name
 
 
-def format_sentence(text: str) -> str:
+def reformat_sentence(text: str) -> str:
     """
-    Remove space between comma and period in a given string.
+    Remove extra spaces between punctuation marks
 
     Parameters
     ----------
@@ -265,7 +267,7 @@ def format_sentence(text: str) -> str:
     str
         The input string with spaces between comma and period removed.
     """
-    return re.sub(r",\s*\.", ",.", text)
+    return re.sub(r"\s*([.,:;?!])\s*", r"\1 ", text)
 
 
 def valid_url(s: str) -> bool:

src/preprocess_helper.py

@@ -155,3 +155,31 @@ def parse_go_sum(file_path: str) -> List[str]:
     dependencies = [match.group(1) for match in regex.finditer(content)]
 
     return dependencies
+
+
+# Java
+def parse_gradle(file_path):
+    with open(file_path) as file:
+        content = file.read()
+
+    regex = re.compile(r"implementation\s+['\"]([^'\"]+)['\"]")
+    dependencies = regex.findall(content)
+
+    return dependencies
+
+
+def parse_maven(file_path):
+    with open(file_path) as file:
+        content = file.read()
+
+    regex = re.compile(
+        r"<dependency>\s*<groupId>([^<]+)</groupId>\s*<artifactId>([^<]+)</artifactId>\s*<version>([^<]+)</version>"
+    )
+    dependencies = []
+    matches = regex.findall(content)
+    for match in matches:
+        group_id, artifact_id, version = match
+        dependency = f"{group_id}:{artifact_id}:{version}"
+        dependencies.append(dependency)
+
+    return dependencies