Spaces:
Sleeping
Sleeping
File size: 6,133 Bytes
978fed5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 | """Workspace file browser and ZIP download components."""
import io
import zipfile
from pathlib import Path
import streamlit as st
MAX_PREVIEW_SIZE = 500_000 # 500KB
MAX_ZIP_FILE_SIZE = 2 * 1024 * 1024 # 2MB
MAX_DISPLAY_FILES = 200
EXCLUDED_DIRS = {
".venv",
"__pycache__",
"node_modules",
".git",
".tox",
".mypy_cache",
".pytest_cache",
"dist",
"build",
".ruff_cache",
}
EXCLUDED_FILES = {"uv.lock", ".DS_Store", "Thumbs.db"}
PREVIEWABLE_EXT = {
".py",
".js",
".ts",
".sh",
".sql",
".html",
".css",
".yaml",
".yml",
".toml",
".json",
".xml",
".cfg",
".ini",
".txt",
".md",
".rst",
".csv",
".tsv",
".log",
".ipynb",
".r",
".c",
".cpp",
".h",
".hpp",
}
LANG_MAP = {
".py": "python",
".js": "javascript",
".ts": "typescript",
".sh": "bash",
".json": "json",
".yaml": "yaml",
".yml": "yaml",
".html": "html",
".css": "css",
".toml": "toml",
".sql": "sql",
".xml": "xml",
".c": "c",
".cpp": "cpp",
".h": "c",
".hpp": "cpp",
".r": "r",
}
def _collect_files(root: Path) -> list[Path]:
"""Collect visible, non-excluded files under root."""
if not root.exists() or not root.is_dir():
return []
result = []
for f in root.rglob("*"):
if not f.is_file():
continue
# Skip hidden files
if f.name.startswith("."):
continue
# Skip files in excluded directories
rel = f.relative_to(root)
if any(part in EXCLUDED_DIRS for part in rel.parts[:-1]):
continue
# Skip excluded file names
if f.name in EXCLUDED_FILES:
continue
result.append(f)
return sorted(result, key=lambda p: p.relative_to(root))
def _format_size(n: int) -> str:
"""Human-readable file size."""
if n < 1024:
return f"{n} B"
elif n < 1024 * 1024:
return f"{n / 1024:.1f} KB"
else:
return f"{n / (1024 * 1024):.1f} MB"
def _render_preview(file_path: Path, key_prefix: str):
"""Render file preview with syntax highlighting."""
ext = file_path.suffix.lower()
if st.button("β Close preview", key=f"{key_prefix}_close"):
del st.session_state[f"{key_prefix}_preview"]
st.rerun()
st.caption(f"π {file_path.name} ({_format_size(file_path.stat().st_size)})")
if ext not in PREVIEWABLE_EXT:
st.warning("Binary file β preview not available.")
return
if file_path.stat().st_size > MAX_PREVIEW_SIZE:
st.warning(f"File too large to preview ({_format_size(file_path.stat().st_size)}).")
return
try:
content = file_path.read_text(encoding="utf-8", errors="replace")
except Exception as e:
st.error(f"Cannot read file: {e}")
return
if ext == ".json":
try:
import json
st.json(json.loads(content))
except Exception:
st.code(content, language="json")
elif ext == ".md":
st.markdown(content)
elif ext in (".csv", ".tsv"):
try:
import pandas as pd
sep = "\t" if ext == ".tsv" else ","
df = pd.read_csv(io.StringIO(content), sep=sep, nrows=200)
st.dataframe(df)
except Exception:
st.code(content)
else:
lang = LANG_MAP.get(ext)
st.code(content, language=lang)
def render_file_browser(root: Path, key_prefix: str = "fb"):
"""Render a file browser with preview for a workspace directory."""
files = _collect_files(root)
if not files:
st.info("No files in workspace.")
return
truncated = len(files) > MAX_DISPLAY_FILES
display_files = files[:MAX_DISPLAY_FILES]
with st.expander(f"π Workspace Files ({len(files)})", expanded=False):
for f in display_files:
rel = str(f.relative_to(root))
try:
size = _format_size(f.stat().st_size)
except OSError:
size = "?"
col_path, col_size, col_btn = st.columns([5, 1, 1])
with col_path:
st.text(f"π {rel}")
with col_size:
st.caption(size)
with col_btn:
if st.button("π", key=f"{key_prefix}_{rel}", help="Preview"):
st.session_state[f"{key_prefix}_preview"] = str(f)
st.rerun()
if truncated:
st.caption(f"Showing first {MAX_DISPLAY_FILES} of {len(files)} files.")
# Preview panel (outside expander so it stays visible)
preview_path = st.session_state.get(f"{key_prefix}_preview")
if preview_path:
p = Path(preview_path)
if p.exists():
_render_preview(p, key_prefix)
def render_workspace_download(root: Path, key_prefix: str = "dl"):
"""Render a ZIP download button for workspace files."""
files = _collect_files(root)
if not files:
return
included = []
excluded = []
for f in files:
rel = str(f.relative_to(root))
try:
size = f.stat().st_size
except OSError:
excluded.append((rel, "cannot read"))
continue
if size > MAX_ZIP_FILE_SIZE:
excluded.append((rel, f"too large ({_format_size(size)})"))
else:
included.append(f)
if not included:
st.caption("No files small enough to package.")
return
buf = io.BytesIO()
with zipfile.ZipFile(buf, "w", zipfile.ZIP_DEFLATED) as zf:
for f in included:
zf.write(f, f.relative_to(root))
buf.seek(0)
st.download_button(
f"π¦ Download Workspace ({len(included)} files)",
data=buf.getvalue(),
file_name="workspace.zip",
mime="application/zip",
key=f"{key_prefix}_zip",
)
if excluded:
with st.expander(f"Excluded from download ({len(excluded)} files)", expanded=False):
for path, reason in excluded:
st.text(f" {path} β {reason}")
|