feat: add infer and tree_magic_mini meta plugins, make zstd internal by default

- Add infer crate as meta plugin for MIME type detection
- Add tree_magic_mini crate as alternative meta plugin for MIME type detection
- Add zstd, infer, tree_magic_mini to default features
- Fix static build script to use musl target instead of glibc+crt-static
- Remove hardcoded shell list from --generate-completion help text
- Fix update() in both new plugins to emit MIME metadata when buffer fills

src/meta_plugin/infer_plugin.rs

@@ -0,0 +1,177 @@
+use crate::common::PIPESIZE;
+use crate::meta_plugin::{
+    process_metadata_outputs, register_meta_plugin, BaseMetaPlugin, MetaPlugin, MetaPluginResponse,
+    MetaPluginType,
+};
+
+#[derive(Debug, Default)]
+pub struct InferMetaPlugin {
+    buffer: Vec<u8>,
+    max_buffer_size: usize,
+    is_finalized: bool,
+    base: BaseMetaPlugin,
+}
+
+impl InferMetaPlugin {
+    pub fn new(
+        options: Option<std::collections::HashMap<String, serde_yaml::Value>>,
+        outputs: Option<std::collections::HashMap<String, serde_yaml::Value>>,
+    ) -> InferMetaPlugin {
+        let mut base = BaseMetaPlugin::new();
+
+        if let Some(opts) = options {
+            for (key, value) in opts {
+                base.options.insert(key, value);
+            }
+        }
+
+        let max_buffer_size = base
+            .options
+            .get("max_buffer_size")
+            .and_then(|v| v.as_u64())
+            .unwrap_or(PIPESIZE as u64) as usize;
+
+        base.outputs.insert(
+            "infer_mime_type".to_string(),
+            serde_yaml::Value::String("infer_mime_type".to_string()),
+        );
+
+        if let Some(outs) = outputs {
+            for (key, value) in outs {
+                base.outputs.insert(key, value);
+            }
+        }
+
+        InferMetaPlugin {
+            buffer: Vec::new(),
+            max_buffer_size,
+            is_finalized: false,
+            base,
+        }
+    }
+}
+
+impl MetaPlugin for InferMetaPlugin {
+    fn meta_type(&self) -> MetaPluginType {
+        MetaPluginType::Infer
+    }
+
+    fn is_finalized(&self) -> bool {
+        self.is_finalized
+    }
+
+    fn set_finalized(&mut self, finalized: bool) {
+        self.is_finalized = finalized;
+    }
+
+    fn set_save_meta(&mut self, save_meta: crate::meta_plugin::SaveMetaFn) {
+        self.base.set_save_meta(save_meta);
+    }
+
+    fn save_meta(&self, name: &str, value: &str) {
+        self.base.save_meta(name, value);
+    }
+
+    fn update(&mut self, data: &[u8]) -> MetaPluginResponse {
+        if self.is_finalized {
+            return MetaPluginResponse {
+                metadata: Vec::new(),
+                is_finalized: true,
+            };
+        }
+
+        let remaining = self.max_buffer_size.saturating_sub(self.buffer.len());
+        let to_add = &data[..data.len().min(remaining)];
+        self.buffer.extend_from_slice(to_add);
+
+        if self.buffer.len() >= self.max_buffer_size {
+            let mime_type = infer::get(&self.buffer)
+                .map(|kind| kind.mime_type().to_string())
+                .unwrap_or_else(|| "application/octet-stream".to_string());
+
+            self.is_finalized = true;
+
+            let metadata = process_metadata_outputs(
+                "infer_mime_type",
+                serde_yaml::Value::String(mime_type),
+                self.base.outputs(),
+            )
+            .map(|m| vec![m])
+            .unwrap_or_default();
+
+            return MetaPluginResponse {
+                metadata,
+                is_finalized: true,
+            };
+        }
+
+        MetaPluginResponse {
+            metadata: Vec::new(),
+            is_finalized: false,
+        }
+    }
+
+    fn finalize(&mut self) -> MetaPluginResponse {
+        if self.is_finalized {
+            return MetaPluginResponse {
+                metadata: Vec::new(),
+                is_finalized: true,
+            };
+        }
+
+        let mime_type = infer::get(&self.buffer)
+            .map(|kind| kind.mime_type().to_string())
+            .unwrap_or_else(|| "application/octet-stream".to_string());
+
+        self.is_finalized = true;
+
+        let metadata = process_metadata_outputs(
+            "infer_mime_type",
+            serde_yaml::Value::String(mime_type),
+            self.base.outputs(),
+        )
+        .map(|m| vec![m])
+        .unwrap_or_default();
+
+        MetaPluginResponse {
+            metadata,
+            is_finalized: true,
+        }
+    }
+
+    fn outputs(&self) -> &std::collections::HashMap<String, serde_yaml::Value> {
+        self.base.outputs()
+    }
+
+    fn outputs_mut(
+        &mut self,
+    ) -> anyhow::Result<&mut std::collections::HashMap<String, serde_yaml::Value>> {
+        Ok(self.base.outputs_mut())
+    }
+
+    fn default_outputs(&self) -> Vec<String> {
+        vec!["infer_mime_type".to_string()]
+    }
+
+    fn options(&self) -> &std::collections::HashMap<String, serde_yaml::Value> {
+        self.base.options()
+    }
+
+    fn options_mut(
+        &mut self,
+    ) -> anyhow::Result<&mut std::collections::HashMap<String, serde_yaml::Value>> {
+        Ok(self.base.options_mut())
+    }
+
+    fn parallel_safe(&self) -> bool {
+        true
+    }
+}
+
+#[ctor::ctor]
+fn register_infer_plugin() {
+    register_meta_plugin(MetaPluginType::Infer, |options, outputs| {
+        Box::new(InferMetaPlugin::new(options, outputs))
+    })
+    .expect("Failed to register InferMetaPlugin");
+}