Files
bookhoard/internal/sync/locators.go
T
john-okeefe b6f507b9e5 fix(sync): understand cross-block text; never store a guessed locator
Tonight's failures all traced to one blind spot: the converter could
only reason about text within a single block. A position at a chapter
heading sends walk-up context (heading + the paragraphs below, joined by
the plugin's block capture); a selection can span several paragraphs.
Neither shape could be verified (containment compared one block against
a multi-block quote, so the CORRECT structural landing at the heading
was rejected) nor matched by text search (it never crossed block
boundaries). The ladder then fell to the percentage rung — which labeled
its char-count guess Precision "exact" — and that confidently-wrong CFI
was stored: reading positions reopened paragraphs away from the true
spot, and a highlight echo overwrote the row's good web CFIs with a
garbage start anchor that made the highlight unpaintable ("disappeared").

Four changes, all in the forward converter and its consumers:

- Quote verification: after the structural walk lands, read the
  whitespace-normalized document text forward from the landing point
  (crossing block boundaries; inline spans join directly so drop-cap
  splits still read as one word). A usable context must be a prefix of
  that stream — which is exactly what device captures are: the text from
  the position onward, or the selection between two anchors. The old
  single-block containment checks remain as secondary acceptance.
- Cross-block text search: the search rung matches against the whole
  document flattened in reading order, with every rune mapped back to
  its source node and offset. A context spanning blocks now matches, and
  the matched extent yields a true range end (EndEPUBCFI) that
  highlights use as their end anchor, threaded through the facade as
  CanonicalLocator.EndCFI.
- Honest labels: the percentage rung returns Precision "percentage" —
  a char-count estimate must never masquerade as an exact anchor.
- Confident-only storage: progress adopts a converted locator solely at
  structural/exact precision (section hrefs keep their legacy handling;
  anything lower stores percentage only), and highlight conversion
  returns CFIs only at structural/exact precision — a low-confidence
  echo yields empty, which applyLWW coalescing turns into preservation
  of the row's existing web CFIs instead of clobbering them.

Tests: walk-up context at a heading verifies structurally and lands in
the heading; a block-spanning context is found by search with a range
end landing in the following paragraph; the percentage rung is honestly
labeled; all drop-cap guards stay green.
2026-09-09 20:15:12 -04:00

177 lines
5.7 KiB
Go

package sync
import (
"log"
"sync"
)
type LocatorSource string
const (
LocatorSourceKOReader LocatorSource = "koreader"
LocatorSourceKobo LocatorSource = "kobo"
LocatorSourceWeb LocatorSource = "web"
)
type CanonicalLocator struct {
CFI string
// EndCFI carries the matched context's range end (text-search
// conversions of selections) so callers can anchor a true highlight
// range across block boundaries.
EndCFI string
Precision string
Percentage float64
}
type DeviceLocator struct {
Position string
Precision string
Percentage float64
}
func isConvertible(formatGroup string) bool {
return formatGroup == string(FormatGroupReflowable)
}
// Converters parse and cache the whole EPUB (spine + content docs), so
// creating one per annotation re-reads the book for every entry. A small
// bounded cache lets one request — or several — share a single parse.
// Servers are the right place for this work: clients stay thin.
var (
converterMu sync.Mutex
converterCache = map[string]*CFIConverter{}
converterOrder []string // insertion order for eviction
)
const maxCachedConverters = 8
func cachedConverter(epubPath string) *CFIConverter {
converterMu.Lock()
defer converterMu.Unlock()
if c, ok := converterCache[epubPath]; ok {
return c
}
c := NewCFIConverter(epubPath)
converterCache[epubPath] = c
converterOrder = append(converterOrder, epubPath)
for len(converterOrder) > maxCachedConverters {
oldest := converterOrder[0]
converterOrder = converterOrder[1:]
delete(converterCache, oldest)
}
return c
}
// SectionPercentageCached resolves the spine-section percentage of a CRE
// xpointer through the shared bounded converter cache, so per-annotation
// lookups parse the EPUB once per book instead of once per annotation.
func SectionPercentageCached(epubPath, xpointer string) float64 {
return cachedConverter(epubPath).SectionPercentage(xpointer)
}
func ConvertToCanonical(
source LocatorSource,
devicePos string,
percentage float64,
contextText string,
formatGroup string,
epubPath string,
kepubPath string,
) CanonicalLocator {
if !isConvertible(formatGroup) || epubPath == "" {
return CanonicalLocator{
CFI: devicePos,
Precision: "passthrough",
Percentage: percentage,
}
}
switch source {
case LocatorSourceKOReader:
if !IsCREXPointer(devicePos) {
return CanonicalLocator{CFI: devicePos, Precision: "already-standard", Percentage: percentage}
}
converter := cachedConverter(epubPath)
result, err := converter.ConvertCREToStandard(devicePos, percentage, contextText)
if err != nil || result == nil {
log.Printf("Bookhoard: locator CRE→CFI conversion failed: %v", err)
return CanonicalLocator{CFI: devicePos, Precision: "fallback", Percentage: percentage}
}
if result.EPUBCFI != "" {
return CanonicalLocator{CFI: result.EPUBCFI, EndCFI: result.EndEPUBCFI, Precision: result.Precision, Percentage: result.Percentage}
}
if result.Href != "" {
return CanonicalLocator{CFI: result.Href, Precision: result.Precision, Percentage: result.Percentage}
}
return CanonicalLocator{CFI: devicePos, Precision: result.Precision, Percentage: percentage}
case LocatorSourceKobo:
if kepubPath == "" {
return CanonicalLocator{CFI: devicePos, Precision: "no-kepub", Percentage: percentage}
}
converter := NewKEPUBCFIConverter(epubPath, kepubPath)
result, err := converter.ConvertKEPUBCFIToStandard(devicePos, percentage, contextText)
if err != nil || result == nil {
log.Printf("Bookhoard: locator KEPUB→CFI conversion failed: %v", err)
return CanonicalLocator{CFI: devicePos, Precision: "fallback", Percentage: percentage}
}
if result.CFI != "" {
return CanonicalLocator{CFI: result.CFI, Precision: result.Precision, Percentage: result.Percentage}
}
return CanonicalLocator{CFI: devicePos, Precision: result.Precision, Percentage: percentage}
default:
return CanonicalLocator{CFI: devicePos, Precision: "passthrough", Percentage: percentage}
}
}
func ConvertFromCanonical(
source LocatorSource,
canonicalCFI string,
percentage float64,
contextText string,
formatGroup string,
epubPath string,
kepubPath string,
) DeviceLocator {
if !isConvertible(formatGroup) || epubPath == "" || canonicalCFI == "" {
return DeviceLocator{
Position: canonicalCFI,
Precision: "passthrough",
Percentage: percentage,
}
}
switch source {
case LocatorSourceKOReader:
converter := cachedConverter(epubPath)
result, err := converter.ConvertStandardToCRE(canonicalCFI, percentage, contextText)
if err != nil || result == nil {
log.Printf("Bookhoard: locator CFI→CRE conversion failed: %v", err)
return DeviceLocator{Position: canonicalCFI, Precision: "fallback", Percentage: percentage}
}
if result.XPointer != "" {
return DeviceLocator{Position: result.XPointer, Precision: result.Precision, Percentage: result.Percentage}
}
return DeviceLocator{Position: canonicalCFI, Precision: result.Precision, Percentage: percentage}
case LocatorSourceKobo:
if kepubPath == "" {
return DeviceLocator{Position: canonicalCFI, Precision: "no-kepub", Percentage: percentage}
}
converter := NewKEPUBCFIConverter(epubPath, kepubPath)
result, err := converter.ConvertStandardCFIToKEPUB(canonicalCFI, percentage, contextText)
if err != nil || result == nil {
log.Printf("Bookhoard: locator CFI→KEPUB conversion failed: %v", err)
return DeviceLocator{Position: canonicalCFI, Precision: "fallback", Percentage: percentage}
}
if result.CFI != "" {
return DeviceLocator{Position: result.CFI, Precision: result.Precision, Percentage: result.Percentage}
}
return DeviceLocator{Position: canonicalCFI, Precision: result.Precision, Percentage: percentage}
default:
return DeviceLocator{Position: canonicalCFI, Precision: "passthrough", Percentage: percentage}
}
}