nikolaandClaude Opus 5.5
5847245638
The PDF parsers shell out to pdftotext, so every machine running money needed poppler-utils installed. scripts/build-bundled.sh now builds a deployable binary that carries its own: pdftotext is compiled in a container from a checksum-pinned poppler release as a fully static musl executable, then embedded with `go build -tags bundled`. The result is one file that runs on any Linux of that architecture with nothing installed alongside it. It is still the real pdftotext, run as a subprocess. Linking poppler through cgo would have cost the pure-Go build, and its C++ text API is not guaranteed to space columns the way pdftotext -layout does, which is what the parsers were tuned on. Only what text extraction needs is compiled in -- no fontconfig, cairo or image codecs -- and its output is byte-identical to a full distro build on the same PDF. At runtime the embedded copy is written to the user cache directory, not /tmp, which servers often mount noexec. It is named by content hash, so a newer build never runs an older copy, and verified before reuse, so a write cut short by a killed process is replaced rather than trusted. `money config` says which pdftotext is in use. The tag is opt-in: plain go build and go test never need the 5 MB executable, which is gitignored rather than committed. Building with the tag for anything but linux/amd64 or linux/arm64 fails with a message saying so. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
66 lines
2.1 KiB
Go
66 lines
2.1 KiB
Go
package parser
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"fmt"
|
|
"os/exec"
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
// pdfToTextTimeout bounds extraction so a malformed PDF cannot wedge an import.
|
|
const pdfToTextTimeout = 2 * time.Minute
|
|
|
|
// pdfToText renders a PDF as text with the original column positions
|
|
// preserved, which is what the statement parsers key off.
|
|
//
|
|
// This shells out to poppler's pdftotext rather than decoding the PDF in Go:
|
|
// the layout reconstruction it does is the whole reason the column-based
|
|
// parsers work, and no Go library matches it. A build made with -tags bundled
|
|
// carries its own copy, so a server needs nothing installed.
|
|
func pdfToText(path string) (string, error) {
|
|
bin, err := pdftotextCommand()
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
|
|
ctx, cancel := context.WithTimeout(context.Background(), pdfToTextTimeout)
|
|
defer cancel()
|
|
|
|
cmd := exec.CommandContext(ctx, bin, "-layout", path, "-")
|
|
var stdout, stderr bytes.Buffer
|
|
cmd.Stdout = &stdout
|
|
cmd.Stderr = &stderr
|
|
|
|
if err := cmd.Run(); err != nil {
|
|
if ctx.Err() == context.DeadlineExceeded {
|
|
return "", fmt.Errorf("pdftotext timed out after %s on %s", pdfToTextTimeout, path)
|
|
}
|
|
if errors := strings.TrimSpace(stderr.String()); errors != "" {
|
|
return "", fmt.Errorf("pdftotext %s: %w: %s", path, err, errors)
|
|
}
|
|
if bin != "pdftotext" {
|
|
// The copy was installed, so failing to start it is about where it
|
|
// was put: a cache directory on a noexec mount is the usual cause.
|
|
return "", fmt.Errorf("bundled pdftotext at %s did not run (is that directory mounted noexec? "+
|
|
"point XDG_CACHE_HOME somewhere else): %w", bin, err)
|
|
}
|
|
if _, lookErr := exec.LookPath("pdftotext"); lookErr != nil {
|
|
return "", fmt.Errorf("pdftotext is not installed (it ships with poppler-utils): %w", lookErr)
|
|
}
|
|
return "", fmt.Errorf("pdftotext %s: %w", path, err)
|
|
}
|
|
return stdout.String(), nil
|
|
}
|
|
|
|
// pages splits pdftotext output on form feeds.
|
|
func pages(text string) []string {
|
|
return strings.Split(text, "\f")
|
|
}
|
|
|
|
// indent counts the leading spaces of a line.
|
|
func indent(line string) int {
|
|
return len(line) - len(strings.TrimLeft(line, " "))
|
|
}
|