academia-mcp 1.3.0__tar.gz → 1.4.0__tar.gz

{academia_mcp-1.3.0 → academia_mcp-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academia-mcp
-Version: 1.3.0
+Version: 1.4.0
 Summary: MCP server that provides different tools to search for scientific publications
 Author-email: Ilya Gusev <phoenixilya@gmail.com>
 Project-URL: Homepage, https://github.com/IlyaGusev/academia_mcp
@@ -22,16 +22,11 @@ Requires-Dist: markdownify==0.14.1
 Requires-Dist: acl-anthology==0.5.2
 Requires-Dist: markdown==3.7.0
 Requires-Dist: types-markdown==3.7.0.20250322
-Requires-Dist: black==25.1.0
-Requires-Dist: mypy==1.16.0
-Requires-Dist: flake8==7.2.0
 Requires-Dist: huggingface-hub>=0.32.4
 Requires-Dist: fire>=0.7.0
-Requires-Dist: pytest>=8.4.1
 Requires-Dist: openai>=1.97.1
 Requires-Dist: jinja2>=3.1.6
 Requires-Dist: datasets>=4.0.0
-Requires-Dist: pytest-asyncio>=1.1.0
 Dynamic: license-file
 
 # Academia MCP

{academia_mcp-1.3.0 → academia_mcp-1.4.0}/academia_mcp/files.py

@@ -5,6 +5,7 @@ from pathlib import Path
 DIR_PATH = Path(__file__).parent
 ROOT_PATH = DIR_PATH.parent
 DEFAULT_WORKSPACE_DIR_PATH: Path = DIR_PATH / "workdir"
+DEFAULT_LATEX_TEMPLATES_DIR_PATH: Path = DIR_PATH / "latex_templates"
 
 
 class WorkspaceDirectory:

{academia_mcp-1.3.0 → academia_mcp-1.4.0}/academia_mcp/server.py

@@ -12,7 +12,12 @@ from .tools.s2_citations import s2_get_citations, s2_get_references
 from .tools.hf_datasets_search import hf_datasets_search
 from .tools.anthology_search import anthology_search
 from .tools.document_qa import document_qa
-from .tools.md_to_pdf import md_to_pdf
+from .tools.latex import (
+    compile_latex_from_file,
+    compile_latex_from_str,
+    get_latex_template,
+    get_latex_templates_list,
+)
 from .tools.web_search import web_search, tavily_web_search, exa_web_search, brave_web_search
 from .tools.visit_webpage import visit_webpage
 from .tools.bitflip import (
@@ -58,7 +63,10 @@ def run(
     server.add_tool(s2_get_references)
     server.add_tool(hf_datasets_search)
     server.add_tool(anthology_search)
-    server.add_tool(md_to_pdf)
+    server.add_tool(compile_latex_from_file)
+    server.add_tool(compile_latex_from_str)
+    server.add_tool(get_latex_template)
+    server.add_tool(get_latex_templates_list)
     server.add_tool(visit_webpage)
 
     if not disable_web_search_tools:

{academia_mcp-1.3.0 → academia_mcp-1.4.0}/academia_mcp/tools/__init__.py

@@ -4,7 +4,12 @@ from .arxiv_download import arxiv_download
 from .hf_datasets_search import hf_datasets_search
 from .s2_citations import s2_get_references, s2_get_citations
 from .document_qa import document_qa
-from .md_to_pdf import md_to_pdf
+from .latex import (
+    compile_latex_from_file,
+    compile_latex_from_str,
+    get_latex_template,
+    get_latex_templates_list,
+)
 from .web_search import web_search, tavily_web_search, exa_web_search, brave_web_search
 from .visit_webpage import visit_webpage
 from .bitflip import extract_bitflip_info, generate_research_proposal, score_research_proposals
@@ -18,7 +23,10 @@ __all__ = [
     "s2_get_citations",
     "hf_datasets_search",
     "document_qa",
-    "md_to_pdf",
+    "compile_latex_from_file",
+    "compile_latex_from_str",
+    "get_latex_template",
+    "get_latex_templates_list",
     "web_search",
     "tavily_web_search",
     "exa_web_search",

academia_mcp-1.4.0/academia_mcp/tools/latex.py

@@ -0,0 +1,151 @@
+import re
+import subprocess
+import shutil
+import tempfile
+import json
+from pathlib import Path
+
+
+from academia_mcp.files import get_workspace_dir, DEFAULT_LATEX_TEMPLATES_DIR_PATH
+
+
+def get_latex_templates_list() -> str:
+    """
+    Get the list of available latex templates.
+    Always use one of the templates from the list.
+
+    Returns a JSON list serialized to a string.
+    Use `json.loads` to deserialize the result.
+    """
+    return json.dumps([str(path.name) for path in DEFAULT_LATEX_TEMPLATES_DIR_PATH.glob("*")])
+
+
+def get_latex_template(template_name: str) -> str:
+    """
+    Get the latex template by name.
+
+    Returns a JSON object serialized to a string.
+    Use `json.loads` to deserialize the result.
+    The structure is: {"template": "...", "style": "..."}
+
+    Args:
+        template_name: The name of the latex template.
+    """
+    template_dir_path = DEFAULT_LATEX_TEMPLATES_DIR_PATH / template_name
+    if not template_dir_path.exists():
+        raise FileNotFoundError(
+            f"Template {template_name} not found in {DEFAULT_LATEX_TEMPLATES_DIR_PATH}"
+        )
+    template_path = template_dir_path / f"{template_name}.tex"
+    style_path = template_dir_path / f"{template_name}.sty"
+    if not template_path.exists():
+        raise FileNotFoundError(f"Template file {template_path} not found in {template_dir_path}")
+    if not style_path.exists():
+        raise FileNotFoundError(f"Style file {style_path} not found in {template_dir_path}")
+    return json.dumps({"template": template_path.read_text(), "style": style_path.read_text()})
+
+
+def compile_latex_from_file(
+    input_filename: str, output_filename: str = "output.pdf", timeout: int = 60
+) -> str:
+    """
+    Compile a latex file.
+
+    Returns a string with the result of the compilation.
+
+    Args:
+        input_filename: The path to the latex file.
+        output_filename: The path to the output pdf file.
+        timeout: The timeout for the compilation. 60 seconds by default.
+    """
+    with open(input_filename, "r", encoding="utf-8") as file:
+        latex_code = file.read()
+    return compile_latex_from_str(latex_code, output_filename, timeout)
+
+
+def compile_latex_from_str(
+    latex_code: str, output_filename: str = "output.pdf", timeout: int = 60
+) -> str:
+    """
+    Compile a latex code.
+
+    Returns a string with the result of the compilation.
+
+    Args:
+        latex_code: The latex code to compile.
+        output_filename: The path to the output pdf file.
+        timeout: The timeout for the compilation. 60 seconds by default.
+    """
+    if shutil.which("pdflatex") is None:
+        return "pdflatex is not installed or not found in PATH."
+
+    destination_name = (
+        output_filename if output_filename.lower().endswith(".pdf") else f"{output_filename}.pdf"
+    )
+
+    try:
+        with tempfile.TemporaryDirectory(
+            dir=str(get_workspace_dir()), prefix="temp_latex_"
+        ) as temp_dir:
+            temp_dir_path = Path(temp_dir)
+            tex_filename = "temp.tex"
+            pdf_filename = "temp.pdf"
+            tex_file_path = temp_dir_path / tex_filename
+            tex_file_path.write_text(latex_code, encoding="utf-8")
+
+            # Detect and copy local .sty packages referenced by \usepackage{...}
+            # Supports optional arguments: \usepackage[opts]{pkgA,pkgB}
+            try:
+                package_names: set[str] = set()
+                for match in re.finditer(r"\\usepackage(?:\[[^\]]*\])?\{([^}]+)\}", latex_code):
+                    for name in match.group(1).split(","):
+                        pkg = name.strip()
+                        if pkg:
+                            package_names.add(pkg)
+
+                for pkg in package_names:
+                    sty_name = f"{pkg}.sty"
+                    for candidate in DEFAULT_LATEX_TEMPLATES_DIR_PATH.rglob(sty_name):
+                        shutil.copyfile(candidate, temp_dir_path / sty_name)
+                        break
+            except Exception:
+                pass
+
+            try:
+                subprocess.run(
+                    [
+                        "pdflatex",
+                        "-interaction=nonstopmode",
+                        tex_filename,
+                    ],
+                    cwd=str(temp_dir_path),
+                    check=True,
+                    capture_output=True,
+                    text=True,
+                    timeout=timeout,
+                )
+            except subprocess.TimeoutExpired:
+                return f"Compilation timed out after {timeout} seconds"
+            except subprocess.CalledProcessError as e:
+                combined_output = (e.stdout or "") + "\n" + (e.stderr or "")
+                error_lines = [
+                    line
+                    for line in combined_output.split("\n")
+                    if ("error" in line.lower() or "!" in line)
+                ]
+                if error_lines:
+                    return "Compilation failed. LaTeX errors:\n" + "\n".join(error_lines)
+                return f"Compilation failed. Full LaTeX output:\n{combined_output}"
+
+            pdf_path = temp_dir_path / pdf_filename
+            output_pdf_path = Path(get_workspace_dir()) / destination_name
+
+            if pdf_path.exists():
+                shutil.move(str(pdf_path), str(output_pdf_path))
+                return f"Compilation successful! PDF file saved as {destination_name}"
+
+            return (
+                "Compilation completed, but PDF file was not created. Check LaTeX code for errors."
+            )
+    except Exception as e:
+        return f"Compilation failed due to an unexpected error: {e}"

{academia_mcp-1.3.0 → academia_mcp-1.4.0}/academia_mcp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academia-mcp
-Version: 1.3.0
+Version: 1.4.0
 Summary: MCP server that provides different tools to search for scientific publications
 Author-email: Ilya Gusev <phoenixilya@gmail.com>
 Project-URL: Homepage, https://github.com/IlyaGusev/academia_mcp
@@ -22,16 +22,11 @@ Requires-Dist: markdownify==0.14.1
 Requires-Dist: acl-anthology==0.5.2
 Requires-Dist: markdown==3.7.0
 Requires-Dist: types-markdown==3.7.0.20250322
-Requires-Dist: black==25.1.0
-Requires-Dist: mypy==1.16.0
-Requires-Dist: flake8==7.2.0
 Requires-Dist: huggingface-hub>=0.32.4
 Requires-Dist: fire>=0.7.0
-Requires-Dist: pytest>=8.4.1
 Requires-Dist: openai>=1.97.1
 Requires-Dist: jinja2>=3.1.6
 Requires-Dist: datasets>=4.0.0
-Requires-Dist: pytest-asyncio>=1.1.0
 Dynamic: license-file
 
 # Academia MCP

{academia_mcp-1.3.0 → academia_mcp-1.4.0}/academia_mcp.egg-info/SOURCES.txt

@@ -21,7 +21,7 @@ academia_mcp/tools/arxiv_search.py
 academia_mcp/tools/bitflip.py
 academia_mcp/tools/document_qa.py
 academia_mcp/tools/hf_datasets_search.py
-academia_mcp/tools/md_to_pdf.py
+academia_mcp/tools/latex.py
 academia_mcp/tools/py.typed
 academia_mcp/tools/s2_citations.py
 academia_mcp/tools/visit_webpage.py
@@ -33,7 +33,7 @@ tests/test_bitflip.py
 tests/test_document_qa.py
 tests/test_extract_json.py
 tests/test_hf_dataset_search.py
-tests/test_md_to_pdf.py
+tests/test_latex.py
 tests/test_s2_citations.py
 tests/test_visit_webpage.py
 tests/test_web_search.py

{academia_mcp-1.3.0 → academia_mcp-1.4.0}/academia_mcp.egg-info/requires.txt

@@ -10,13 +10,8 @@ markdownify==0.14.1
 acl-anthology==0.5.2
 markdown==3.7.0
 types-markdown==3.7.0.20250322
-black==25.1.0
-mypy==1.16.0
-flake8==7.2.0
 huggingface-hub>=0.32.4
 fire>=0.7.0
-pytest>=8.4.1
 openai>=1.97.1
 jinja2>=3.1.6
 datasets>=4.0.0
-pytest-asyncio>=1.1.0

{academia_mcp-1.3.0 → academia_mcp-1.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "academia-mcp"
-version = "1.3.0"
+version = "1.4.0"
 description = "MCP server that provides different tools to search for scientific publications"
 readme = "README.md"
 authors = [
@@ -29,15 +29,19 @@ dependencies = [
     "acl-anthology==0.5.2",
     "markdown==3.7.0",
     "types-markdown==3.7.0.20250322",
-    "black==25.1.0",
-    "mypy==1.16.0",
-    "flake8==7.2.0",
     "huggingface-hub>=0.32.4",
     "fire>=0.7.0",
-    "pytest>=8.4.1",
     "openai>=1.97.1",
     "jinja2>=3.1.6",
     "datasets>=4.0.0",
+]
+
+[dependency-groups]
+dev = [
+    "black==25.1.0",
+    "mypy==1.16.0",
+    "flake8==7.2.0",
+    "pytest>=8.4.1",
     "pytest-asyncio>=1.1.0",
 ]
 

academia_mcp-1.4.0/tests/test_latex.py

@@ -0,0 +1,41 @@
+import json
+import tempfile
+from pathlib import Path
+
+from academia_mcp.tools.latex import (
+    compile_latex_from_file,
+    compile_latex_from_str,
+    get_latex_template,
+    get_latex_templates_list,
+)
+
+
+def test_latex_get_latex_templates_list() -> None:
+    templates_list = json.loads(get_latex_templates_list())
+    assert len(templates_list) > 0
+    assert "agents4science_2025" in templates_list
+
+
+def test_latex_get_latex_template() -> None:
+    result = json.loads(get_latex_template("agents4science_2025"))
+    assert "template" in result
+    assert "style" in result
+    assert result["template"] is not None
+    assert result["style"] is not None
+
+
+def test_latex_compile_latex_from_str() -> None:
+    template = json.loads(get_latex_template("agents4science_2025"))
+    result = compile_latex_from_str(template["template"], "test.pdf")
+    assert "Compilation successful" in result
+
+
+def test_latex_compile_latex_from_file() -> None:
+    template = json.loads(get_latex_template("agents4science_2025"))
+    with tempfile.TemporaryDirectory() as temp_dir:
+        temp_dir_path = Path(temp_dir)
+        tex_filename = "temp.tex"
+        tex_file_path = temp_dir_path / tex_filename
+        tex_file_path.write_text(template["template"], encoding="utf-8")
+        result = compile_latex_from_file(str(tex_file_path), "test.pdf")
+    assert "Compilation successful" in result

academia_mcp-1.3.0/academia_mcp/tools/md_to_pdf.py

@@ -1,411 +0,0 @@
-import markdown
-import re
-import os
-import subprocess
-import shutil
-import xml.dom.minidom
-import xml.etree.ElementTree as etree
-from typing import Optional, Any
-
-from markdown.core import Markdown
-
-from academia_mcp.files import get_workspace_dir
-
-
-START_SINGLE_QUOTE_RE = re.compile(r"(^|\s|\")'")
-START_DOUBLE_QUOTE_RE = re.compile(r"(^|\s|'|`)\"")
-END_DOUBLE_QUOTE_RE = re.compile(r'"(,|\.|\s|$)')
-
-
-MAIN_TEMPLATE = """\\documentclass{{article}}
-\\usepackage[utf8]{{inputenc}}
-\\usepackage[T1]{{fontenc}}
-\\usepackage{{textcomp}}
-\\usepackage{{amsmath}}
-\\usepackage{{float}}
-\\usepackage{{graphicx}}
-\\usepackage{{enumitem}}
-\\usepackage{{quoting}}
-\\usepackage{{booktabs}}
-\\usepackage{{caption}}
-\\usepackage{{siunitx}}
-\\sisetup{{
-  group-separator = {{,}},
-  output-decimal-marker = {{.}}
-}}
-\\usepackage{{hyperref}}
-
-\\author{{Holosophos}}
-
-\\begin{{document}}
-
-{latex_content}
-
-\\end{{document}}"""
-
-
-IMAGE_TEMPLATE = """\\begin{{figure}}[H]
-\\centering
-\\includegraphics[width=\\linewidth]{{{src}}}
-\\caption{{{alt}}}
-\\end{{figure}}"""
-
-
-TABLE_TEMPLATE = """
-\\begin{{table}}[h]
-\\begin{{tabular}}{{{descriptor}}}
-{core}
-\\hline
-\\end{{tabular}}
-\\\\[5pt]
-\\caption{{{caption}}}
-\\end{{table}}
-"""
-
-ITEMIZE_TEMPLATE = """
-\\begin{{itemize}}
-{content}
-\\end{{itemize}}
-"""
-
-QUOTE_TEMPLATE = """
-\\begin{{quotation}}
-{content}
-\\end{{quotation}}
-"""
-
-VERBATIM_TEMPLATE = """
-\\begin{{verbatim}}
-{content}
-\\end{{verbatim}}
-"""
-
-
-MAKETITLE = """
-% ----------------------------------------------------------------
-\\maketitle
-% ----------------------------------------------------------------
-"""
-
-
-def inline_html_latex(text: str) -> str:
-    out = text
-    if re.search(r"“.*?”", text, flags=re.DOTALL):
-        out = out.replace("“", "\\enquote{").replace("”", "}")
-    if re.search(r"‘.*?’", text, flags=re.DOTALL):
-        out = out.replace("‘", "\\enquote{").replace("’", "}")
-    if re.search(r"“.*?“", text, flags=re.DOTALL):
-        out = out.replace("“", "\\enquote{", 1).replace("“", "}", 1)
-    if re.search(r"«.*?»", text, flags=re.DOTALL):
-        out = out.replace("«", "\\enquote{").replace("»", "}")
-    out = out.replace("...", "\\dots")
-    out = out.replace("…", "\\dots")
-    out = out.replace("–", "--")
-    out = out.replace("—", "---")
-    out = out.replace("\\|", "|")
-    return out
-
-
-def unescape_html_entities(text: str) -> str:
-    mapping = {
-        "&": "&",
-        "&lt;": "<",
-        "&gt;": ">",
-        "&quot;": '"',
-    }
-    for k, v in mapping.items():
-        text = text.replace(k, v)
-    return text
-
-
-def escape_latex_entities(text: str) -> str:
-    out = unescape_html_entities(text)
-    out = out.replace("%", "\\%")
-    out = out.replace("&", "\\&")
-    out = out.replace("#", "\\#")
-    out = START_SINGLE_QUOTE_RE.sub(r"\g<1>`", out)
-    out = START_DOUBLE_QUOTE_RE.sub(r"\g<1>``", out)
-    out = END_DOUBLE_QUOTE_RE.sub(r"''\g<1>", out)
-    return out
-
-
-class LaTeXExtension(markdown.Extension):
-    def __init__(self, configs: Optional[Any] = None) -> None:
-        self.reset()
-
-    def extendMarkdown(self, md: Markdown) -> None:
-        self.md = md
-        latex_tp = LaTeXTreeProcessor()
-        math_pp = MathTextPostProcessor()
-        table_pp = TableTextPostProcessor()
-        image_pp = ImageTextPostProcessor()
-        link_pp = LinkTextPostProcessor()
-        unescape_html_pp = UnescapeHtmlTextPostProcessor()
-
-        md.treeprocessors.register(latex_tp, "latex", 20)
-        md.postprocessors.register(unescape_html_pp, "unescape_html", 20)
-        md.postprocessors.register(math_pp, "math", 20)
-        md.postprocessors.register(image_pp, "image", 20)
-        md.postprocessors.register(table_pp, "table", 20)
-        md.postprocessors.register(link_pp, "link", 20)
-
-    def reset(self) -> None:
-        pass
-
-
-class LaTeXTreeProcessor(markdown.treeprocessors.Treeprocessor):
-    def run(self, doc: etree.Element) -> None:
-        latex_text = self.tolatex(doc)
-        doc.clear()
-        latex_node = etree.Element("plaintext")
-        latex_node.text = latex_text
-        doc.append(latex_node)
-
-    def tolatex(self, ournode: etree.Element) -> str:
-        buf = ""
-        subcontent = ""
-
-        if ournode.text:
-            subcontent += escape_latex_entities(ournode.text)
-
-        for child in list(ournode):
-            subcontent += self.tolatex(child)
-
-        tag = ournode.tag
-        if tag == "h1":
-            buf += "\n\\title{%s}\n" % subcontent
-            buf += MAKETITLE
-        elif tag == "h2":
-            buf += "\n\n\\section{%s}\n" % subcontent
-        elif tag == "h3":
-            buf += "\n\n\\subsection{%s}\n" % subcontent
-        elif tag == "h4":
-            buf += "\n\\subsubsection{%s}\n" % subcontent
-        elif tag == "hr":
-            buf += "\\noindent\\makebox[\\linewidth]{\\rule{\\linewidth}{0.4pt}}"
-        elif tag == "ul":
-            buf += ITEMIZE_TEMPLATE.format(content=subcontent.strip())
-        elif tag == "ol":
-            buf += " \\begin{enumerate}"
-            if "start" in ournode.attrib:
-                start = int(ournode.attrib["start"]) - 1
-                buf += "\\setcounter{enumi}{" + str(start) + "}"
-            buf += f"\n{subcontent}\n\\end{{enumerate}}"
-        elif tag == "li":
-            buf += "\n  \\item %s" % subcontent.strip()
-        elif tag == "blockquote":
-            buf += QUOTE_TEMPLATE.format(content=subcontent.strip())
-        elif tag == "pre":
-            buf += VERBATIM_TEMPLATE.format(content=subcontent.strip())
-        elif tag == "q":
-            buf += "`%s'" % subcontent.strip()
-        elif tag == "p":
-            buf += "\n%s\n" % subcontent.strip()
-        elif tag == "sup":
-            buf += "\\footnote{%s}" % subcontent.strip()
-        elif tag == "strong":
-            buf += "\\textbf{%s}" % subcontent.strip()
-        elif tag == "em":
-            buf += "\\emph{%s}" % subcontent.strip()
-        elif tag == "table":
-            buf += "\n\n<table>%s</table>\n\n" % subcontent
-        elif tag == "thead":
-            buf += "<thead>%s</thead>" % subcontent
-        elif tag == "tbody":
-            buf += "<tbody>%s</tbody>" % subcontent
-        elif tag == "tr":
-            buf += "<tr>%s</tr>" % subcontent
-        elif tag == "th":
-            buf += "<th>%s</th>" % subcontent
-        elif tag == "td":
-            buf += "<td>%s</td>" % subcontent
-        elif tag == "img":
-            buf += '<img src="%s" alt="%s" />' % (
-                ournode.get("src"),
-                ournode.get("alt"),
-            )
-        elif tag == "a":
-            href = ournode.get("href")
-            assert href
-            buf += '<a href="%s">%s</a>' % (
-                escape_latex_entities(href),
-                subcontent,
-            )
-        else:
-            buf = subcontent
-
-        if ournode.tail:
-            buf += escape_latex_entities(ournode.tail)
-
-        return buf
-
-
-class Table2Latex:
-    def convert_markdown_table(self, instr: str) -> str:
-        lines = instr.split("\n")
-        headers = lines[0].strip("|").split("|")
-        cols = len(headers)
-        buf = (
-            "\\begin{table}[h]\n\\centering\n\\begin{tabular}{|"
-            + "|".join(["l"] * cols)
-            + "|}\n\\hline\n"
-        )
-        buf += (
-            " & ".join([f"\\textbf{{{header.strip()}}}" for header in headers]) + " \\\\\n\\hline\n"
-        )
-        for line in lines[2:]:
-            cells = line.strip("|").split("|")
-            buf += " & ".join([cell.strip() for cell in cells]) + " \\\\\n\\hline\n"
-        buf += "\\end{tabular}\n\\end{table}"
-        return buf
-
-
-class Img2Latex:
-    def convert(self, instr: str) -> str:
-        dom = xml.dom.minidom.parseString(instr)
-        img = dom.documentElement
-        assert img is not None
-        src = img.getAttribute("src")
-        alt = img.getAttribute("alt")
-        return IMAGE_TEMPLATE.format(src=src, alt=alt)
-
-
-class Link2Latex:
-    def convert(self, instr: str) -> str:
-        dom = xml.dom.minidom.parseString(instr)
-        link = dom.documentElement
-        assert link is not None
-        href = link.getAttribute("href")
-        matches = re.search(r">([^<]+)", instr)
-        desc = ""
-        if matches:
-            desc = matches.group(1)
-        return r"\href{%s}{%s}" % (href, desc) if href != desc else r"\url{%s}" % href
-
-
-class ImageTextPostProcessor(markdown.postprocessors.Postprocessor):
-    def run(self, instr: str) -> str:
-        converter = Img2Latex()
-        new_blocks = []
-        for block in instr.split("\n\n"):
-            stripped = block.strip()
-            if stripped.startswith("<img"):
-                stripped = re.sub(r"<\/?plaintext[^>]*>", "", stripped, flags=re.IGNORECASE)
-                new_blocks.append(converter.convert(stripped).strip())
-            else:
-                new_blocks.append(block)
-        return "\n\n".join(new_blocks)
-
-
-class LinkTextPostProcessor(markdown.postprocessors.Postprocessor):
-    def run(self, instr: str) -> str:
-        converter = Link2Latex()
-        new_blocks = []
-        for block in instr.split("\n\n"):
-            stripped = block.strip()
-            matches = re.findall(r"<a[^>]*>[^<]+</a>", stripped)
-            if matches:
-                for match in matches:
-                    stripped = stripped.replace(match, converter.convert(match).strip())
-                new_blocks.append(stripped)
-            else:
-                new_blocks.append(block)
-        return "\n\n".join(new_blocks)
-
-
-class UnescapeHtmlTextPostProcessor(markdown.postprocessors.Postprocessor):
-    def run(self, text: str) -> str:
-        return unescape_html_entities(inline_html_latex(text))
-
-
-class MathTextPostProcessor(markdown.postprocessors.Postprocessor):
-    def run(self, instr: str) -> str:
-        instr = re.sub(r"\$\$([^\$]*)\$\$", r"\\[\1\\]", instr)
-        instr = re.sub(r"\$([^\$]*)\$", r"\\(\1\\)", instr)
-        instr = instr.replace("\\lt", "<").replace(" * ", " \\cdot ").replace("\\del", "\\partial")
-        return instr
-
-
-class TableTextPostProcessor(markdown.postprocessors.Postprocessor):
-    def run(self, instr: str) -> str:
-        converter = Table2Latex()
-        new_blocks = []
-        for block in instr.split("\n\n"):
-            stripped = block.strip()
-            if re.match(r"\|.*\|", stripped):  # Check for Markdown table
-                new_blocks.append(converter.convert_markdown_table(stripped).strip())
-            else:
-                new_blocks.append(block)
-        return "\n\n".join(new_blocks)
-
-
-def convert_md_to_latex(md_content: str) -> str:
-    md = markdown.Markdown(extensions=[LaTeXExtension()])
-    latex_content = md.convert(md_content)
-    latex_content = re.sub(r"<\/?plaintext[^>]*>", "", latex_content, flags=re.IGNORECASE)
-    return MAIN_TEMPLATE.format(latex_content=latex_content)
-
-
-def md_to_pdf(markdown_text: str, output_filename: str = "output") -> str:
-    """
-    Convert Markdown to PDF via LaTeX.
-
-    Args:
-        markdown_text: Markdown text
-        output_filename: Output filename (without extension)
-
-    Returns:
-        Message about the compilation result
-    """
-
-    latex_code = convert_md_to_latex(markdown_text)
-
-    temp_dir = get_workspace_dir() / "temp_latex"
-    temp_dir.mkdir(parents=True, exist_ok=True)
-
-    tex_file_path = temp_dir / "temp.tex"
-    with open(tex_file_path, "w", encoding="utf-8") as f:
-        f.write(latex_code)
-
-    if shutil.which("pdflatex") is None:
-        shutil.rmtree(temp_dir, ignore_errors=True)
-        return "pdflatex is not installed or not found in PATH."
-
-    try:
-        subprocess.run(
-            [
-                "pdflatex",
-                "-interaction=nonstopmode",
-                "-output-directory",
-                temp_dir,
-                tex_file_path,
-            ],
-            check=True,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            timeout=30,
-        )
-
-    except subprocess.TimeoutExpired:
-        shutil.rmtree(temp_dir, ignore_errors=True)
-        return "Compilation timed out after 30 seconds"
-    except subprocess.CalledProcessError as e:
-        error_msg = e.stdout.decode("utf-8")
-        error_lines = [
-            line for line in error_msg.split("\n") if "error" in line.lower() or "!" in line
-        ]
-        shutil.rmtree(temp_dir, ignore_errors=True)
-        if error_lines:
-            return "Compilation failed. LaTeX errors:\n" + "\n".join(error_lines)
-        return f"Compilation failed. Full LaTeX output:\n{error_msg}"
-
-    pdf_path = os.path.join(temp_dir, "temp.pdf")
-    output_pdf_path = os.path.join(get_workspace_dir(), f"{output_filename}.pdf")
-
-    if os.path.exists(pdf_path):
-        shutil.move(pdf_path, output_pdf_path)
-        shutil.rmtree(temp_dir, ignore_errors=True)
-        return f"Compilation successful! PDF file saved as {output_filename}.pdf"
-
-    shutil.rmtree(temp_dir, ignore_errors=True)
-    return "Compilation completed, but PDF file was not created. Check LaTeX code for errors."

academia_mcp-1.3.0/tests/test_md_to_pdf.py

@@ -1,114 +0,0 @@
-from academia_mcp.tools.md_to_pdf import convert_md_to_latex, md_to_pdf
-
-
-TEST_MD_BASIC = """
-# Markdown syntax guide
-
-## Headers
-
-### This is a Heading h3
-###### This is a Heading h6
-
-## Emphasis
-
-*This text will be italic*
-_This will also be italic_
-
-**This text will be bold**
-__This will also be bold__
-
-_You **can** combine them_
-"""
-
-TEST_MD_TABLES = """
-## Tables
-
-| Left columns  | Right columns |
-| ------------- |:-------------:|
-| left foo      | right foo     |
-| left bar      | right bar     |
-| left baz      | right baz     |
-"""
-
-TEST_MD_LINKS = """
-## Links
-
-You may be using [Markdown Live Preview](https://markdownlivepreview.com/).
-"""
-
-TEST_MD_IMAGES = """
-## Images
-
-![This is an alt text.](/image/sample.webp "This is a sample image.")
-"""
-
-TEST_MD_LISTS = """
-## Lists
-
-### Unordered
-
-* Item 1
-* Item 2
-* Item 2a
-* Item 2b
-    * Item 3a
-    * Item 3b
-
-### Ordered
-
-1. Item 1
-2. Item 2
-3. Item 3
-    1. Item 3a
-    2. Item 3b
-"""
-
-
-def test_md_to_latex_basic() -> None:
-    latex = convert_md_to_latex(TEST_MD_BASIC)
-    assert "\\documentclass{article}" in latex
-    assert "\\title{Markdown syntax guide}" in latex
-    assert "\\section{Headers}" in latex
-    assert "\\section{Emphasis}" in latex
-    assert "\\subsection{This is a Heading h3}" in latex
-    assert "\\emph{This text will be italic}" in latex
-    assert "\\emph{This will also be italic}" in latex
-    assert "\\textbf{This text will be bold}" in latex
-    assert "\\textbf{This will also be bold}" in latex
-    assert "\\emph{You \\textbf{can} combine them}" in latex
-
-
-def test_md_to_latex_tables() -> None:
-    latex = convert_md_to_latex(TEST_MD_TABLES)
-    assert "\\begin{table}[h]" in latex
-    assert "\\begin{tabular}{|l|l|}" in latex
-    assert "left foo & right foo" in latex
-
-
-def test_md_to_latex_links() -> None:
-    latex = convert_md_to_latex(TEST_MD_LINKS)
-    assert (
-        "You may be using \\href{https://markdownlivepreview.com/}{Markdown Live Preview}." in latex
-    )
-
-
-def test_md_to_latex_images() -> None:
-    latex = convert_md_to_latex(TEST_MD_IMAGES)
-    assert "\\begin{figure}" in latex
-    assert "\\includegraphics[width=\\linewidth]{/image/sample.webp}" in latex
-    assert "\\caption{This is an alt text.}" in latex
-    assert "\\end{figure}" in latex
-
-
-def test_md_to_latex_lists() -> None:
-    latex = convert_md_to_latex(TEST_MD_LISTS)
-    assert "\\begin{itemize}" in latex
-    assert "\\end{itemize}" in latex
-    assert "\\begin{enumerate}" in latex
-    assert "\\end{enumerate}" in latex
-    assert "\\item Item 3a" in latex
-
-
-def test_md_to_pdf() -> None:
-    result = md_to_pdf(TEST_MD_LISTS, "output")
-    assert "Compilation successful" in result