fix(pdf): replace dslipak/pdf with pdfcpu bookmark+content-stream extraction
Use PDF outline (bookmarks) for chapter titles and page ranges, then extract text from per-page content streams via pdfcpu ExtractContent. This avoids the indefinite hang caused by dslipak/pdf trying to resolve custom font ToUnicode CMaps on publisher PDFs. - parsePDF: decrypt → ExtractContent → Bookmarks → chaptersFromBookmarks - chaptersFromBookmarks: flatten bookmark tree, skip front/back matter (Cover, Insert, Title Page, Copyright, Appendix), assign page ranges - extractTextFromContentStream: handle TJ arrays (concat literal strings, skip hex glyph arrays and kerning numbers) + single Tj strings - Falls back to paragraph-splitting when no bookmarks present - Build verified; test PDF produces 9 chapters with proper titles
This commit is contained in:
@@ -3,7 +3,23 @@ module github.com/libnovel/backend
|
||||
go 1.26.1
|
||||
|
||||
require (
|
||||
github.com/getsentry/sentry-go v0.43.0
|
||||
github.com/hibiken/asynq v0.26.0
|
||||
github.com/hibiken/asynq/x v0.0.0-20260203063626-d704b68a426d
|
||||
github.com/meilisearch/meilisearch-go v0.36.1
|
||||
github.com/minio/minio-go/v7 v7.0.98
|
||||
github.com/pdfcpu/pdfcpu v0.11.1
|
||||
github.com/prometheus/client_golang v1.23.2
|
||||
github.com/redis/go-redis/v9 v9.18.0
|
||||
github.com/yuin/goldmark v1.8.2
|
||||
go.opentelemetry.io/contrib/bridges/otelslog v0.17.0
|
||||
go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.67.0
|
||||
go.opentelemetry.io/otel v1.42.0
|
||||
go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploghttp v0.18.0
|
||||
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.42.0
|
||||
go.opentelemetry.io/otel/log v0.18.0
|
||||
go.opentelemetry.io/otel/sdk v1.42.0
|
||||
go.opentelemetry.io/otel/sdk/log v0.18.0
|
||||
golang.org/x/net v0.51.0
|
||||
)
|
||||
|
||||
@@ -13,12 +29,9 @@ require (
|
||||
github.com/cenkalti/backoff/v5 v5.0.3 // indirect
|
||||
github.com/cespare/xxhash/v2 v2.3.0 // indirect
|
||||
github.com/clipperhouse/uax29/v2 v2.2.0 // indirect
|
||||
github.com/davecgh/go-spew v1.1.1 // indirect
|
||||
github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
|
||||
github.com/dslipak/pdf v0.0.2 // indirect
|
||||
github.com/dustin/go-humanize v1.0.1 // indirect
|
||||
github.com/felixge/httpsnoop v1.0.4 // indirect
|
||||
github.com/getsentry/sentry-go v0.43.0 // indirect
|
||||
github.com/go-ini/ini v1.67.0 // indirect
|
||||
github.com/go-logr/logr v1.4.3 // indirect
|
||||
github.com/go-logr/stdr v1.2.2 // indirect
|
||||
@@ -28,41 +41,25 @@ require (
|
||||
github.com/hhrutter/lzw v1.0.0 // indirect
|
||||
github.com/hhrutter/pkcs7 v0.2.0 // indirect
|
||||
github.com/hhrutter/tiff v1.0.2 // indirect
|
||||
github.com/hibiken/asynq v0.26.0 // indirect
|
||||
github.com/hibiken/asynq/x v0.0.0-20260203063626-d704b68a426d // indirect
|
||||
github.com/klauspost/compress v1.18.2 // indirect
|
||||
github.com/klauspost/cpuid/v2 v2.2.11 // indirect
|
||||
github.com/klauspost/crc32 v1.3.0 // indirect
|
||||
github.com/mattn/go-runewidth v0.0.19 // indirect
|
||||
github.com/meilisearch/meilisearch-go v0.36.1 // indirect
|
||||
github.com/minio/crc64nvme v1.1.1 // indirect
|
||||
github.com/minio/md5-simd v1.1.2 // indirect
|
||||
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
|
||||
github.com/pdfcpu/pdfcpu v0.11.1 // indirect
|
||||
github.com/philhofer/fwd v1.2.0 // indirect
|
||||
github.com/pkg/errors v0.9.1 // indirect
|
||||
github.com/pmezard/go-difflib v1.0.0 // indirect
|
||||
github.com/prometheus/client_golang v1.23.2 // indirect
|
||||
github.com/prometheus/client_model v0.6.2 // indirect
|
||||
github.com/prometheus/common v0.66.1 // indirect
|
||||
github.com/prometheus/procfs v0.16.1 // indirect
|
||||
github.com/redis/go-redis/v9 v9.18.0 // indirect
|
||||
github.com/robfig/cron/v3 v3.0.1 // indirect
|
||||
github.com/rs/xid v1.6.0 // indirect
|
||||
github.com/spf13/cast v1.10.0 // indirect
|
||||
github.com/tinylib/msgp v1.6.1 // indirect
|
||||
github.com/yuin/goldmark v1.8.2 // indirect
|
||||
go.opentelemetry.io/auto/sdk v1.2.1 // indirect
|
||||
go.opentelemetry.io/contrib/bridges/otelslog v0.17.0 // indirect
|
||||
go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.67.0 // indirect
|
||||
go.opentelemetry.io/otel v1.42.0 // indirect
|
||||
go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploghttp v0.18.0 // indirect
|
||||
go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.42.0 // indirect
|
||||
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.42.0 // indirect
|
||||
go.opentelemetry.io/otel/log v0.18.0 // indirect
|
||||
go.opentelemetry.io/otel/metric v1.42.0 // indirect
|
||||
go.opentelemetry.io/otel/sdk v1.42.0 // indirect
|
||||
go.opentelemetry.io/otel/sdk/log v0.18.0 // indirect
|
||||
go.opentelemetry.io/otel/trace v1.42.0 // indirect
|
||||
go.opentelemetry.io/proto/otlp v1.9.0 // indirect
|
||||
go.uber.org/atomic v1.11.0 // indirect
|
||||
@@ -78,5 +75,4 @@ require (
|
||||
google.golang.org/grpc v1.79.2 // indirect
|
||||
google.golang.org/protobuf v1.36.11 // indirect
|
||||
gopkg.in/yaml.v2 v2.4.0 // indirect
|
||||
gopkg.in/yaml.v3 v3.0.1 // indirect
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user