pdfdoc: page markers, the map for long documents, page ranges, grep
Pure render function on a *pdftext.Doc with no I/O: the whole text with page markers when it fits, otherwise a map (title, outline with page numbers, leading pages and how to ask for more), a page range, or grep results with page numbers. Every length is in runes. Co-Authored-By: ornith-1.5-35b-a3b <ornith-1.5-35b-a3b@llama.cpp.invalid>
This commit is contained in:
ornith-1.5-35b-a3b
@@ -0,0 +1,249 @@
|
||||
package pdfdoc_test
|
||||
|
||||
// P5a task 05: rendering an extracted document for an agent — the whole text with page markers,
|
||||
// the map for a long document, a page range, and grep.
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
"unicode/utf8"
|
||||
|
||||
"git.wntrmute.dev/kyle/sift/internal/pdfdoc"
|
||||
"git.wntrmute.dev/kyle/sift/internal/pdftext"
|
||||
)
|
||||
|
||||
func small() *pdftext.Doc {
|
||||
return &pdftext.Doc{
|
||||
Meta: pdftext.Meta{Pages: 3, Title: "Three Pages", Outline: []pdftext.OutlineItem{{Title: "1 Intro", Page: 1, Level: 1}, {Title: "2 Fox", Page: 2, Level: 1}, {Title: "2.1 Den", Page: 2, Level: 2}}},
|
||||
Text: []string{"Chapter one begins here.\nSecond line.\n", " The quick brown fox is on page two.\nIt jumps.", "Last page."},
|
||||
}
|
||||
}
|
||||
|
||||
// big returns n pages of about 1,000 characters each, every line naming its page.
|
||||
func big(n int) *pdftext.Doc {
|
||||
d := &pdftext.Doc{Meta: pdftext.Meta{Pages: n, Title: "Long Thesis", Outline: []pdftext.OutlineItem{{Title: "1 Introduction", Page: 1, Level: 1}, {Title: "2 Method", Page: 12, Level: 1}, {Title: "2.3 Setup", Page: 15, Level: 2}}}}
|
||||
for p := 1; p <= n; p++ {
|
||||
var lines []string
|
||||
for l := 1; l <= 12; l++ {
|
||||
lines = append(lines, fmt.Sprintf("page %d line %d lorem ipsum dolor sit amet consectetur adipiscing elit sed do eiusmod", p, l))
|
||||
}
|
||||
if p == 37 {
|
||||
lines[4] = "the Needle is here on page 37"
|
||||
}
|
||||
d.Text = append(d.Text, strings.Join(lines, "\n"))
|
||||
}
|
||||
return d
|
||||
}
|
||||
|
||||
func TestFull(t *testing.T) {
|
||||
want := "--- page 1 ---\n\nChapter one begins here.\nSecond line.\n\n--- page 2 ---\n\nThe quick brown fox is on page two.\nIt jumps.\n\n--- page 3 ---\n\nLast page."
|
||||
if got := pdfdoc.Full(small()); got != want {
|
||||
t.Errorf("Full =\n%q\nwant\n%q", got, want)
|
||||
}
|
||||
if pdfdoc.Marker(12) != "--- page 12 ---" {
|
||||
t.Errorf("Marker(12) = %q", pdfdoc.Marker(12))
|
||||
}
|
||||
}
|
||||
|
||||
func TestWholeDocumentWhenItFits(t *testing.T) {
|
||||
r, err := pdfdoc.Render(small(), pdfdoc.Options{OutCap: 10000})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if r.Map || r.First != 1 || r.Last != 3 || r.Content != pdfdoc.Full(small()) {
|
||||
t.Errorf("got %+v", r)
|
||||
}
|
||||
}
|
||||
|
||||
func TestMapForALongDocument(t *testing.T) {
|
||||
d := big(60) // ~60k characters
|
||||
r, err := pdfdoc.Render(d, pdfdoc.Options{OutCap: 20000})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !r.Map || r.First != 1 || r.Last < 1 {
|
||||
t.Fatalf("got Map=%v First=%d Last=%d, want a map from page 1", r.Map, r.First, r.Last)
|
||||
}
|
||||
c := r.Content
|
||||
for _, want := range []string{
|
||||
"# Long Thesis\n",
|
||||
"60 pages · ~",
|
||||
"## Outline\n",
|
||||
"- 1 Introduction (p. 1)\n",
|
||||
"- 2 Method (p. 12)\n",
|
||||
" - 2.3 Setup (p. 15)\n", // level 2 is indented two spaces
|
||||
`pages="a-b"`,
|
||||
`grep="pattern"`,
|
||||
"--- page 1 ---",
|
||||
} {
|
||||
if !strings.Contains(c, want) {
|
||||
t.Errorf("map lacks %q", want)
|
||||
}
|
||||
}
|
||||
if utf8.RuneCountInString(c) > 20000 {
|
||||
t.Errorf("map is %d characters, over OutCap 20000", utf8.RuneCountInString(c))
|
||||
}
|
||||
// Leading pages take at most a quarter of the cap, and only whole pages.
|
||||
if strings.Contains(c, fmt.Sprintf("--- page %d ---", r.Last+1)) {
|
||||
t.Errorf("content has page %d past Last %d", r.Last+1, r.Last)
|
||||
}
|
||||
if !strings.Contains(c, fmt.Sprintf("page %d line 12", r.Last)) {
|
||||
t.Errorf("the last page shown (%d) is cut; pages in a map are whole", r.Last)
|
||||
}
|
||||
idx := strings.Index(c, "--- page 1 ---")
|
||||
if pagesPart := c[idx:]; utf8.RuneCountInString(pagesPart) > 20000/4 {
|
||||
t.Errorf("leading pages take %d characters, over OutCap/4", utf8.RuneCountInString(pagesPart))
|
||||
}
|
||||
}
|
||||
|
||||
func TestMapNotesPartialExtraction(t *testing.T) {
|
||||
d := big(30)
|
||||
d.Pages = 2500 // the child stopped at its page cap
|
||||
r, _ := pdfdoc.Render(d, pdfdoc.Options{OutCap: 5000})
|
||||
if !strings.Contains(r.Content, "2500 pages") || !strings.Contains(r.Content, "pages 1-30 extracted") {
|
||||
t.Errorf("map must say how much was extracted:\n%s", r.Content[:min(600, len(r.Content))])
|
||||
}
|
||||
}
|
||||
|
||||
func TestUntitledAndNoOutline(t *testing.T) {
|
||||
d := big(40)
|
||||
d.Title, d.Outline = "", nil
|
||||
r, _ := pdfdoc.Render(d, pdfdoc.Options{OutCap: 5000})
|
||||
if !strings.HasPrefix(r.Content, "# Untitled PDF\n") || strings.Contains(r.Content, "## Outline") {
|
||||
t.Errorf("untitled, outline-less map:\n%s", r.Content[:min(400, len(r.Content))])
|
||||
}
|
||||
}
|
||||
|
||||
func TestPages(t *testing.T) {
|
||||
d := big(60)
|
||||
for _, tc := range []struct {
|
||||
spec string
|
||||
first, last int
|
||||
}{
|
||||
{"2-3", 2, 3},
|
||||
{"7", 7, 7},
|
||||
{" 58- ", 58, 60},
|
||||
{"60-60", 60, 60},
|
||||
} {
|
||||
r, err := pdfdoc.Render(d, pdfdoc.Options{Pages: tc.spec, OutCap: 200000})
|
||||
if err != nil {
|
||||
t.Errorf("%q: %v", tc.spec, err)
|
||||
continue
|
||||
}
|
||||
if r.Map || r.First != tc.first || r.Last != tc.last {
|
||||
t.Errorf("%q: First %d Last %d Map %v, want %d-%d", tc.spec, r.First, r.Last, r.Map, tc.first, tc.last)
|
||||
}
|
||||
if !strings.HasPrefix(r.Content, pdfdoc.Marker(tc.first)+"\n\n") || strings.Contains(r.Content, pdfdoc.Marker(tc.last+1)) || (tc.first > 1 && strings.Contains(r.Content, pdfdoc.Marker(tc.first-1)+"\n")) {
|
||||
t.Errorf("%q: wrong pages in content: %.120q…", tc.spec, r.Content)
|
||||
}
|
||||
}
|
||||
for _, bad := range []string{"0-1", "5-4", "61", "999", "a-b", "1-2-3", "", "-5"} {
|
||||
if bad == "" {
|
||||
continue // empty means "no range", tested above
|
||||
}
|
||||
_, err := pdfdoc.Render(d, pdfdoc.Options{Pages: bad, OutCap: 200000})
|
||||
if !errors.Is(err, pdfdoc.ErrBadPages) {
|
||||
t.Errorf("%q: %v, want ErrBadPages", bad, err)
|
||||
}
|
||||
}
|
||||
_, err := pdfdoc.Render(d, pdfdoc.Options{Pages: "61", OutCap: 200000})
|
||||
if err == nil || !strings.Contains(err.Error(), "pages out of range (1-60)") {
|
||||
t.Errorf("out-of-range message: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// A range is at most 100 pages and at most OutCap characters, cut at a whole page with a note
|
||||
// that says how to continue.
|
||||
func TestPagesAreCapped(t *testing.T) {
|
||||
d := big(300)
|
||||
r, err := pdfdoc.Render(d, pdfdoc.Options{Pages: "1-300", OutCap: 1 << 30})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if r.Last != 100 || !strings.Contains(r.Note, `pages="101-300"`) {
|
||||
t.Errorf("1-300: Last %d note %q; want 100 and a pointer to 101-300", r.Last, r.Note)
|
||||
}
|
||||
r, _ = pdfdoc.Render(d, pdfdoc.Options{Pages: "10-40", OutCap: 5000})
|
||||
if utf8.RuneCountInString(r.Content) > 5000 || r.First != 10 || r.Last < 10 || r.Last >= 40 {
|
||||
t.Errorf("10-40 under a 5000 cap: First %d Last %d, %d chars", r.First, r.Last, utf8.RuneCountInString(r.Content))
|
||||
}
|
||||
if !strings.Contains(r.Note, fmt.Sprintf(`pages="%d-40"`, r.Last+1)) {
|
||||
t.Errorf("note %q must point at the rest", r.Note)
|
||||
}
|
||||
// One page bigger than the cap is truncated rather than dropped.
|
||||
huge := &pdftext.Doc{Meta: pdftext.Meta{Pages: 1}, Text: []string{strings.Repeat("w ", 10000)}}
|
||||
r, _ = pdfdoc.Render(huge, pdfdoc.Options{Pages: "1", OutCap: 1000})
|
||||
if r.First != 1 || r.Last != 1 || utf8.RuneCountInString(r.Content) > 1000 || r.Note == "" {
|
||||
t.Errorf("oversized single page: %+v (%d chars)", r, utf8.RuneCountInString(r.Content))
|
||||
}
|
||||
}
|
||||
|
||||
func TestGrep(t *testing.T) {
|
||||
d := big(60)
|
||||
r, err := pdfdoc.Render(d, pdfdoc.Options{Grep: "needle", OutCap: 200000})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if r.GrepHits != 1 || r.First != 0 || r.Map {
|
||||
t.Errorf("got %+v", r)
|
||||
}
|
||||
for _, want := range []string{
|
||||
`grep "needle": 1 match`,
|
||||
"p. 37- page 37 line 4",
|
||||
"p. 37: the Needle is here on page 37",
|
||||
"p. 37- page 37 line 6",
|
||||
} {
|
||||
if !strings.Contains(r.Content, want) {
|
||||
t.Errorf("grep output lacks %q:\n%s", want, r.Content)
|
||||
}
|
||||
}
|
||||
// Smart case: an upper-case letter makes the pattern case-sensitive.
|
||||
if r, _ := pdfdoc.Render(d, pdfdoc.Options{Grep: "NEEDLE", OutCap: 200000}); r.GrepHits != 0 {
|
||||
t.Errorf("NEEDLE matched %d times, want 0 (case-sensitive)", r.GrepHits)
|
||||
}
|
||||
if r, _ := pdfdoc.Render(d, pdfdoc.Options{Grep: "Needle", OutCap: 200000}); r.GrepHits != 1 {
|
||||
t.Errorf("Needle matched %d times, want 1", r.GrepHits)
|
||||
}
|
||||
// No match is an answer, not an error.
|
||||
r, err = pdfdoc.Render(d, pdfdoc.Options{Grep: "zebra", OutCap: 200000})
|
||||
if err != nil || r.GrepHits != 0 || !strings.Contains(r.Content, `grep "zebra": no matches`) {
|
||||
t.Errorf("no match: %+v %v", r, err)
|
||||
}
|
||||
// Within a page range.
|
||||
r, _ = pdfdoc.Render(d, pdfdoc.Options{Grep: "line 3 ", Pages: "5-6", OutCap: 200000})
|
||||
if r.GrepHits != 2 || strings.Contains(r.Content, "p. 7") {
|
||||
t.Errorf("grep in 5-6: %d hits\n%s", r.GrepHits, r.Content)
|
||||
}
|
||||
}
|
||||
|
||||
func TestGrepLimits(t *testing.T) {
|
||||
d := big(200)
|
||||
r, err := pdfdoc.Render(d, pdfdoc.Options{Grep: "lorem", OutCap: 1 << 30}) // 2,399 matches: every line but the needle
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if r.GrepHits != 2399 || strings.Count(r.Content, ": page ") != 100 || !strings.Contains(r.Content, "showing the first 100") {
|
||||
t.Errorf("hits %d, shown %d", r.GrepHits, strings.Count(r.Content, ": page "))
|
||||
}
|
||||
if _, err := pdfdoc.Render(d, pdfdoc.Options{Grep: strings.Repeat("a", 201), OutCap: 1000}); !errors.Is(err, pdfdoc.ErrBadGrep) {
|
||||
t.Errorf("201-byte pattern: %v, want ErrBadGrep", err)
|
||||
}
|
||||
if _, err := pdfdoc.Render(d, pdfdoc.Options{Grep: "(unclosed", OutCap: 1000}); !errors.Is(err, pdfdoc.ErrBadGrep) {
|
||||
t.Errorf("bad regexp: %v, want ErrBadGrep", err)
|
||||
}
|
||||
// RE2 is linear: the classic catastrophic pattern over a 1 MB page finishes quickly.
|
||||
evil := &pdftext.Doc{Meta: pdftext.Meta{Pages: 1}, Text: []string{strings.Repeat("a", 1<<20) + "!"}}
|
||||
start := time.Now()
|
||||
_, _ = pdfdoc.Render(evil, pdfdoc.Options{Grep: "(a+)+$", OutCap: 1000})
|
||||
if d := time.Since(start); d > time.Second {
|
||||
t.Errorf("(a+)+$ took %v", d)
|
||||
}
|
||||
// Output stays under the cap.
|
||||
r, _ = pdfdoc.Render(d, pdfdoc.Options{Grep: "lorem", OutCap: 3000})
|
||||
if utf8.RuneCountInString(r.Content) > 3000 {
|
||||
t.Errorf("grep output %d characters over a 3000 cap", utf8.RuneCountInString(r.Content))
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user