Documentation
¶
Overview ¶
Package extract turns supported raw content into plain text for chunking. It handles text/plain and text/markdown; markdown is currently embedded as-is (heading-aware handling is a later refinement). Newlines are normalized to "\n" so a file's content hash is stable across platforms.
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Extractor ¶
type Extractor struct{}
Extractor extracts text from supported content types. Its zero value is ready.
type Router ¶
type Router struct {
// contains filtered or unexported fields
}
Router dispatches extraction to the first of its Extractors that supports a content type, presenting many format adapters as the single Extractor port the use cases consume. The composition root builds it from the concrete adapters (text, docx, pdf, ...).
Source Files
Click to show internal directories.
Click to hide internal directories.