pgpdf

pig build pkg pgpdf;		# build rpm / deb with pig

pig repo add pgdg pigsty -u   # add both repo and update cache

pig install pgpdf;		# install via package name, for the active PG version

pig install pgpdf -v 18;   # install for PG 18
pig install pgpdf -v 17;   # install for PG 17
pig install pgpdf -v 16;   # install for PG 16
pig install pgpdf -v 15;   # install for PG 15
pig install pgpdf -v 14;   # install for PG 14
pig install pgpdf -v 13;   # install for PG 13

shared_preload_libraries = 'pgpdf';

CREATE EXTENSION pgpdf;

wget https://wiki.postgresql.org/images/e/ea/PostgreSQL_Introduction.pdf -O /tmp/pgintro.pdf
wget https://pdfobject.com/pdf/sample.pdf -O /tmp/sample.pdf

CREATE EXTENSION pgpdf;
SELECT '/tmp/pgintro.pdf'::pdf;

                                       pdf                                        
----------------------------------------------------------------------------------
 PostgreSQL Introduction                                                         +
 Digoal.Zhou                                                                     +
 7/20/2011Catalog                                                                +
  PostgreSQL Origin 

SELECT pg_read_binary_file('/tmp/pgintro.pdf')::bytea::pdf;

CREATE TABLE pdfs(name text primary key, doc pdf);

INSERT INTO pdfs VALUES ('pgintro', '/tmp/pgintro.pdf');
INSERT INTO pdfs VALUES ('pgintro', '/tmp/sample.pdf');

SELECT 'Below is the PDF we received ' || '/tmp/pgintro.pdf'::pdf;

SELECT upper('/tmp/pgintro.pdf'::pdf::text);

SELECT name
FROM pdfs
WHERE doc::text LIKE '%Postgres%';

SELECT '/tmp/pgintro.pdf'::pdf::text @@ to_tsquery('postgres');

 ?column? 
----------
 t
(1 row)

SELECT '/tmp/pgintro.pdf'::pdf::text @@ to_tsquery('oracle');

 ?column? 
----------
 f
(1 row)

CREATE EXTENSION pg_trgm;

SELECT similarity('/tmp/pgintro.pdf'::pdf::text, '/tmp/sample.pdf'::pdf::text);

SELECT pdf_title('/tmp/pgintro.pdf');

        pdf_title        
-------------------------
 PostgreSQL Introduction
(1 row)

SELECT pdf_author('/tmp/pgintro.pdf');

 pdf_author 
------------
 周正中
(1 row)

SELECT pdf_num_pages('/tmp/pgintro.pdf');

 pdf_num_pages 
---------------
            24
(1 row)

SELECT pdf_page('/tmp/pgintro.pdf', 1);

           pdf_page           
------------------------------
 Catalog                     +
  PostgreSQL Origin         +
  Layout                    +
  Features                  +
  Enterprise Class Attribute+
  Case
(1 row)

SELECT pdf_subject('/tmp/pgintro.pdf');

 pdf_subject 
-------------
 
(1 row)

SELECT pdf_creation('/tmp/pgintro.pdf');

       pdf_creation       
--------------------------
 Wed Jul 20 11:13:37 2011
(1 row)

SELECT pdf_modification('/tmp/pgintro.pdf');

     pdf_modification     
--------------------------
 Wed Jul 20 11:13:37 2011
(1 row)

SELECT pdf_creator('/tmp/pgintro.pdf');

            pdf_creator             
------------------------------------
 Microsoft® Office PowerPoint® 2007
(1 row)

SELECT pdf_metadata('/tmp/pgintro.pdf');

 pdf_metadata 
--------------
 
(1 row)

SELECT pdf_version('/tmp/pgintro.pdf');

 pdf_version 
-------------
 PDF-1.5
(1 row)

CREATE EXTENSION pgpdf;

docker pull florents/pgpdf:pg17

docker run --name pgpdf -p 5432:5432 -e POSTGRES_PASSWORD=pass florents/pgpdf:pg17

PGPASSWORD=pass psql -h localhost -p 5432 -U postgres