Move a few functions that have been copy-pasted around to shared module.

Cargo.lock

@@ -1340,6 +1340,7 @@ dependencies = [
  "hex",
  "log",
  "rand",
+ "regex",
 ]
 
 [[package]]

pageserver/src/basebackup.rs

@@ -1,12 +1,11 @@
 use log::*;
-use regex::Regex;
-use std::fmt;
 use std::io::Write;
 use tar::Builder;
 use walkdir::WalkDir;
 
 use crate::ZTimelineId;
 
+use postgres_ffi::relfile_utils::*;
 use zenith_utils::lsn::Lsn;
 
 ///
@@ -99,73 +98,6 @@ pub fn send_snapshot_tarball(
     Ok(())
 }
 
-// formats:
-// <oid>
-// <oid>_<fork name>
-// <oid>.<segment number>
-// <oid>_<fork name>.<segment number>
-
-#[derive(Debug)]
-struct FilePathError {
-    msg: String,
-}
-
-impl FilePathError {
-    fn new(msg: &str) -> FilePathError {
-        FilePathError {
-            msg: msg.to_string(),
-        }
-    }
-}
-
-impl From<core::num::ParseIntError> for FilePathError {
-    fn from(e: core::num::ParseIntError) -> Self {
-        return FilePathError {
-            msg: format!("invalid filename: {}", e),
-        };
-    }
-}
-
-impl fmt::Display for FilePathError {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "invalid filename")
-    }
-}
-
-fn forkname_to_forknum(forkname: Option<&str>) -> Result<u32, FilePathError> {
-    match forkname {
-        // "main" is not in filenames, it's implicit if the fork name is not present
-        None => Ok(0),
-        Some("fsm") => Ok(1),
-        Some("vm") => Ok(2),
-        Some("init") => Ok(3),
-        Some(_) => Err(FilePathError::new("invalid forkname")),
-    }
-}
-
-fn parse_filename(fname: &str) -> Result<(u32, u32, u32), FilePathError> {
-    let re = Regex::new(r"^(?P<relnode>\d+)(_(?P<forkname>[a-z]+))?(\.(?P<segno>\d+))?$").unwrap();
-
-    let caps = re
-        .captures(fname)
-        .ok_or_else(|| FilePathError::new("invalid relation data file name"))?;
-
-    let relnode_str = caps.name("relnode").unwrap().as_str();
-    let relnode = u32::from_str_radix(relnode_str, 10)?;
-
-    let forkname = caps.name("forkname").map(|f| f.as_str());
-    let forknum = forkname_to_forknum(forkname)?;
-
-    let segno_match = caps.name("segno");
-    let segno = if segno_match.is_none() {
-        0
-    } else {
-        u32::from_str_radix(segno_match.unwrap().as_str(), 10)?
-    };
-
-    Ok((relnode, forknum, segno))
-}
-
 ///
 /// Parse a path, relative to the root of PostgreSQL data directory, as
 /// a PostgreSQL relation data file.
@@ -189,7 +121,7 @@ fn parse_rel_file_path(path: &str) -> Result<(), FilePathError> {
      * <oid>.<segment number>
      */
     if let Some(fname) = path.strip_prefix("global/") {
-        let (_relnode, _forknum, _segno) = parse_filename(fname)?;
+        let (_relnode, _forknum, _segno) = parse_relfilename(fname)?;
 
         Ok(())
     } else if let Some(dbpath) = path.strip_prefix("base/") {
@@ -205,7 +137,7 @@ fn parse_rel_file_path(path: &str) -> Result<(), FilePathError> {
             return Err(FilePathError::new("invalid relation data file name"));
         };
 
-        let (_relnode, _forknum, _segno) = parse_filename(fname)?;
+        let (_relnode, _forknum, _segno) = parse_relfilename(fname)?;
 
         Ok(())
     } else if let Some(_) = path.strip_prefix("pg_tblspc/") {

pageserver/src/restore_local_repo.rs

@@ -11,11 +11,8 @@
 //
 
 use log::*;
-use regex::Regex;
-use std::fmt;
 
 use std::cmp::max;
-use std::error::Error;
 use std::fs;
 use std::fs::File;
 use std::io::Read;
@@ -31,6 +28,7 @@ use crate::waldecoder::{decode_wal_record, WalStreamDecoder};
 use crate::PageServerConf;
 use crate::ZTimelineId;
 use postgres_ffi::pg_constants;
+use postgres_ffi::relfile_utils::*;
 use postgres_ffi::xlog_utils::*;
 use zenith_utils::lsn::Lsn;
 
@@ -370,75 +368,3 @@ fn restore_wal(timeline: &dyn Timeline, timelineid: ZTimelineId, startpoint: Lsn
 
     Ok(())
 }
-
-#[derive(Debug, Clone)]
-struct FilePathError {
-    msg: String,
-}
-
-impl Error for FilePathError {
-    fn description(&self) -> &str {
-        &self.msg
-    }
-}
-impl FilePathError {
-    fn new(msg: &str) -> FilePathError {
-        FilePathError {
-            msg: msg.to_string(),
-        }
-    }
-}
-
-impl From<core::num::ParseIntError> for FilePathError {
-    fn from(e: core::num::ParseIntError) -> Self {
-        return FilePathError {
-            msg: format!("invalid filename: {}", e),
-        };
-    }
-}
-
-impl fmt::Display for FilePathError {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "invalid filename")
-    }
-}
-
-fn forkname_to_forknum(forkname: Option<&str>) -> Result<u32, FilePathError> {
-    match forkname {
-        // "main" is not in filenames, it's implicit if the fork name is not present
-        None => Ok(0),
-        Some("fsm") => Ok(1),
-        Some("vm") => Ok(2),
-        Some("init") => Ok(3),
-        Some(_) => Err(FilePathError::new("invalid forkname")),
-    }
-}
-
-// formats:
-// <oid>
-// <oid>_<fork name>
-// <oid>.<segment number>
-// <oid>_<fork name>.<segment number>
-
-fn parse_relfilename(fname: &str) -> Result<(u32, u32, u32), FilePathError> {
-    let re = Regex::new(r"^(?P<relnode>\d+)(_(?P<forkname>[a-z]+))?(\.(?P<segno>\d+))?$").unwrap();
-
-    let caps = re
-        .captures(fname)
-        .ok_or_else(|| FilePathError::new("invalid relation data file name"))?;
-
-    let relnode_str = caps.name("relnode").unwrap().as_str();
-    let relnode = u32::from_str_radix(relnode_str, 10)?;
-
-    let forkname = caps.name("forkname").map(|f| f.as_str());
-    let forknum = forkname_to_forknum(forkname)?;
-
-    let segno_match = caps.name("segno");
-    let segno = if segno_match.is_none() {
-        0
-    } else {
-        u32::from_str_radix(segno_match.unwrap().as_str(), 10)?
-    };
-
-    Ok((relnode, forknum, segno))
-}

pageserver/src/restore_s3.rs

@@ -24,6 +24,7 @@ use futures::future;
 
 use crate::{page_cache, PageServerConf};
 use postgres_ffi::pg_constants;
+use postgres_ffi::relfile_utils::*;
 
 struct Storage {
     region: Region,
@@ -128,44 +129,6 @@ async fn restore_chunk(conf: &PageServerConf) -> Result<(), S3Error> {
     Ok(())
 }
 
-#[derive(Debug)]
-struct FilePathError {
-    msg: String,
-}
-
-impl FilePathError {
-    fn new(msg: &str) -> FilePathError {
-        FilePathError {
-            msg: msg.to_string(),
-        }
-    }
-}
-
-impl From<core::num::ParseIntError> for FilePathError {
-    fn from(e: core::num::ParseIntError) -> Self {
-        return FilePathError {
-            msg: format!("invalid filename: {}", e),
-        };
-    }
-}
-
-impl fmt::Display for FilePathError {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "invalid filename")
-    }
-}
-
-fn forkname_to_forknum(forkname: Option<&str>) -> Result<u32, FilePathError> {
-    match forkname {
-        // "main" is not in filenames, it's implicit if the fork name is not present
-        None => Ok(0),
-        Some("fsm") => Ok(1),
-        Some("vm") => Ok(2),
-        Some("init") => Ok(3),
-        Some(_) => Err(FilePathError::new("invalid forkname")),
-    }
-}
-
 #[derive(Debug)]
 struct ParsedBaseImageFileName {
     pub spcnode: u32,

postgres_ffi/Cargo.toml

@@ -9,6 +9,7 @@ edition = "2018"
 [dependencies]
 chrono = "0.4.19"
 rand = "0.8.3"
+regex = "1.4.5"
 bytes = "1.0.1"
 byteorder = "1.4.3"
 anyhow = "1.0"

postgres_ffi/src/lib.rs

@@ -4,6 +4,7 @@
 include!(concat!(env!("OUT_DIR"), "/bindings.rs"));
 
 pub mod pg_constants;
+pub mod relfile_utils;
 pub mod xlog_utils;
 
 use bytes::{Buf, Bytes, BytesMut};

postgres_ffi/src/relfile_utils.rs

@@ -0,0 +1,92 @@
+///
+/// Common utilities for dealing with PostgreSQL relation files.
+///
+use regex::Regex;
+use std::error::Error;
+use std::fmt;
+
+#[derive(Debug, Clone)]
+pub struct FilePathError {
+    msg: String,
+}
+
+impl Error for FilePathError {
+    fn description(&self) -> &str {
+        &self.msg
+    }
+}
+impl FilePathError {
+    pub fn new(msg: &str) -> FilePathError {
+        FilePathError {
+            msg: msg.to_string(),
+        }
+    }
+}
+
+impl From<core::num::ParseIntError> for FilePathError {
+    fn from(e: core::num::ParseIntError) -> Self {
+        return FilePathError {
+            msg: format!("invalid filename: {}", e),
+        };
+    }
+}
+
+impl fmt::Display for FilePathError {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "invalid filename")
+    }
+}
+
+/// Convert Postgres relation file's fork suffix to fork number.
+pub fn forkname_to_number(forkname: Option<&str>) -> Result<u8, FilePathError> {
+    match forkname {
+        // "main" is not in filenames, it's implicit if the fork name is not present
+        None => Ok(0),
+        Some("fsm") => Ok(1),
+        Some("vm") => Ok(2),
+        Some("init") => Ok(3),
+        Some(_) => Err(FilePathError::new("invalid forkname")),
+    }
+}
+
+/// Convert Postgres fork number to the right suffix of the relation data file.
+pub fn forknumber_to_name(forknum: u8) -> Option<&'static str> {
+    match forknum {
+        0 => None,
+        1 => Some("fsm"),
+        2 => Some("vm"),
+        3 => Some("init"),
+        _ => panic!("unrecognized fork number"),
+    }
+}
+
+///
+/// Parse a filename of a relation file. Returns (relfilenode, forknum, segno) tuple.
+///
+/// Formats:
+/// <oid>
+/// <oid>_<fork name>
+/// <oid>.<segment number>
+/// <oid>_<fork name>.<segment number>
+pub fn parse_relfilename(fname: &str) -> Result<(u32, u8, u32), FilePathError> {
+    let re = Regex::new(r"^(?P<relnode>\d+)(_(?P<forkname>[a-z]+))?(\.(?P<segno>\d+))?$").unwrap();
+
+    let caps = re
+        .captures(fname)
+        .ok_or_else(|| FilePathError::new("invalid relation data file name"))?;
+
+    let relnode_str = caps.name("relnode").unwrap().as_str();
+    let relnode = u32::from_str_radix(relnode_str, 10)?;
+
+    let forkname = caps.name("forkname").map(|f| f.as_str());
+    let forknum = forkname_to_number(forkname)?;
+
+    let segno_match = caps.name("segno");
+    let segno = if segno_match.is_none() {
+        0
+    } else {
+        u32::from_str_radix(segno_match.unwrap().as_str(), 10)?
+    };
+
+    Ok((relnode, forknum, segno))
+}